├── LICENSE ├── README.md ├── images ├── data.txt └── dishit.png └── json_data.txt /LICENSE: -------------------------------------------------------------------------------- 1 | Apache License 2 | Version 2.0, January 2004 3 | http://www.apache.org/licenses/ 4 | 5 | TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION 6 | 7 | 1. Definitions. 8 | 9 | "License" shall mean the terms and conditions for use, reproduction, 10 | and distribution as defined by Sections 1 through 9 of this document. 11 | 12 | "Licensor" shall mean the copyright owner or entity authorized by 13 | the copyright owner that is granting the License. 14 | 15 | "Legal Entity" shall mean the union of the acting entity and all 16 | other entities that control, are controlled by, or are under common 17 | control with that entity. For the purposes of this definition, 18 | "control" means (i) the power, direct or indirect, to cause the 19 | direction or management of such entity, whether by contract or 20 | otherwise, or (ii) ownership of fifty percent (50%) or more of the 21 | outstanding shares, or (iii) beneficial ownership of such entity. 22 | 23 | "You" (or "Your") shall mean an individual or Legal Entity 24 | exercising permissions granted by this License. 25 | 26 | "Source" form shall mean the preferred form for making modifications, 27 | including but not limited to software source code, documentation 28 | source, and configuration files. 29 | 30 | "Object" form shall mean any form resulting from mechanical 31 | transformation or translation of a Source form, including but 32 | not limited to compiled object code, generated documentation, 33 | and conversions to other media types. 34 | 35 | "Work" shall mean the work of authorship, whether in Source or 36 | Object form, made available under the License, as indicated by a 37 | copyright notice that is included in or attached to the work 38 | (an example is provided in the Appendix below). 39 | 40 | "Derivative Works" shall mean any work, whether in Source or Object 41 | form, that is based on (or derived from) the Work and for which the 42 | editorial revisions, annotations, elaborations, or other modifications 43 | represent, as a whole, an original work of authorship. For the purposes 44 | of this License, Derivative Works shall not include works that remain 45 | separable from, or merely link (or bind by name) to the interfaces of, 46 | the Work and Derivative Works thereof. 47 | 48 | "Contribution" shall mean any work of authorship, including 49 | the original version of the Work and any modifications or additions 50 | to that Work or Derivative Works thereof, that is intentionally 51 | submitted to Licensor for inclusion in the Work by the copyright owner 52 | or by an individual or Legal Entity authorized to submit on behalf of 53 | the copyright owner. For the purposes of this definition, "submitted" 54 | means any form of electronic, verbal, or written communication sent 55 | to the Licensor or its representatives, including but not limited to 56 | communication on electronic mailing lists, source code control systems, 57 | and issue tracking systems that are managed by, or on behalf of, the 58 | Licensor for the purpose of discussing and improving the Work, but 59 | excluding communication that is conspicuously marked or otherwise 60 | designated in writing by the copyright owner as "Not a Contribution." 61 | 62 | "Contributor" shall mean Licensor and any individual or Legal Entity 63 | on behalf of whom a Contribution has been received by Licensor and 64 | subsequently incorporated within the Work. 65 | 66 | 2. Grant of Copyright License. Subject to the terms and conditions of 67 | this License, each Contributor hereby grants to You a perpetual, 68 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 69 | copyright license to reproduce, prepare Derivative Works of, 70 | publicly display, publicly perform, sublicense, and distribute the 71 | Work and such Derivative Works in Source or Object form. 72 | 73 | 3. Grant of Patent License. Subject to the terms and conditions of 74 | this License, each Contributor hereby grants to You a perpetual, 75 | worldwide, non-exclusive, no-charge, royalty-free, irrevocable 76 | (except as stated in this section) patent license to make, have made, 77 | use, offer to sell, sell, import, and otherwise transfer the Work, 78 | where such license applies only to those patent claims licensable 79 | by such Contributor that are necessarily infringed by their 80 | Contribution(s) alone or by combination of their Contribution(s) 81 | with the Work to which such Contribution(s) was submitted. If You 82 | institute patent litigation against any entity (including a 83 | cross-claim or counterclaim in a lawsuit) alleging that the Work 84 | or a Contribution incorporated within the Work constitutes direct 85 | or contributory patent infringement, then any patent licenses 86 | granted to You under this License for that Work shall terminate 87 | as of the date such litigation is filed. 88 | 89 | 4. Redistribution. You may reproduce and distribute copies of the 90 | Work or Derivative Works thereof in any medium, with or without 91 | modifications, and in Source or Object form, provided that You 92 | meet the following conditions: 93 | 94 | (a) You must give any other recipients of the Work or 95 | Derivative Works a copy of this License; and 96 | 97 | (b) You must cause any modified files to carry prominent notices 98 | stating that You changed the files; and 99 | 100 | (c) You must retain, in the Source form of any Derivative Works 101 | that You distribute, all copyright, patent, trademark, and 102 | attribution notices from the Source form of the Work, 103 | excluding those notices that do not pertain to any part of 104 | the Derivative Works; and 105 | 106 | (d) If the Work includes a "NOTICE" text file as part of its 107 | distribution, then any Derivative Works that You distribute must 108 | include a readable copy of the attribution notices contained 109 | within such NOTICE file, excluding those notices that do not 110 | pertain to any part of the Derivative Works, in at least one 111 | of the following places: within a NOTICE text file distributed 112 | as part of the Derivative Works; within the Source form or 113 | documentation, if provided along with the Derivative Works; or, 114 | within a display generated by the Derivative Works, if and 115 | wherever such third-party notices normally appear. The contents 116 | of the NOTICE file are for informational purposes only and 117 | do not modify the License. You may add Your own attribution 118 | notices within Derivative Works that You distribute, alongside 119 | or as an addendum to the NOTICE text from the Work, provided 120 | that such additional attribution notices cannot be construed 121 | as modifying the License. 122 | 123 | You may add Your own copyright statement to Your modifications and 124 | may provide additional or different license terms and conditions 125 | for use, reproduction, or distribution of Your modifications, or 126 | for any such Derivative Works as a whole, provided Your use, 127 | reproduction, and distribution of the Work otherwise complies with 128 | the conditions stated in this License. 129 | 130 | 5. Submission of Contributions. Unless You explicitly state otherwise, 131 | any Contribution intentionally submitted for inclusion in the Work 132 | by You to the Licensor shall be under the terms and conditions of 133 | this License, without any additional terms or conditions. 134 | Notwithstanding the above, nothing herein shall supersede or modify 135 | the terms of any separate license agreement you may have executed 136 | with Licensor regarding such Contributions. 137 | 138 | 6. Trademarks. This License does not grant permission to use the trade 139 | names, trademarks, service marks, or product names of the Licensor, 140 | except as required for reasonable and customary use in describing the 141 | origin of the Work and reproducing the content of the NOTICE file. 142 | 143 | 7. Disclaimer of Warranty. Unless required by applicable law or 144 | agreed to in writing, Licensor provides the Work (and each 145 | Contributor provides its Contributions) on an "AS IS" BASIS, 146 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or 147 | implied, including, without limitation, any warranties or conditions 148 | of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A 149 | PARTICULAR PURPOSE. You are solely responsible for determining the 150 | appropriateness of using or redistributing the Work and assume any 151 | risks associated with Your exercise of permissions under this License. 152 | 153 | 8. Limitation of Liability. In no event and under no legal theory, 154 | whether in tort (including negligence), contract, or otherwise, 155 | unless required by applicable law (such as deliberate and grossly 156 | negligent acts) or agreed to in writing, shall any Contributor be 157 | liable to You for damages, including any direct, indirect, special, 158 | incidental, or consequential damages of any character arising as a 159 | result of this License or out of the use or inability to use the 160 | Work (including but not limited to damages for loss of goodwill, 161 | work stoppage, computer failure or malfunction, or any and all 162 | other commercial damages or losses), even if such Contributor 163 | has been advised of the possibility of such damages. 164 | 165 | 9. Accepting Warranty or Additional Liability. While redistributing 166 | the Work or Derivative Works thereof, You may choose to offer, 167 | and charge a fee for, acceptance of support, warranty, indemnity, 168 | or other liability obligations and/or rights consistent with this 169 | License. However, in accepting such obligations, You may act only 170 | on Your own behalf and on Your sole responsibility, not on behalf 171 | of any other Contributor, and only if You agree to indemnify, 172 | defend, and hold each Contributor harmless for any liability 173 | incurred by, or claims asserted against, such Contributor by reason 174 | of your accepting any such warranty or additional liability. 175 | 176 | END OF TERMS AND CONDITIONS 177 | 178 | APPENDIX: How to apply the Apache License to your work. 179 | 180 | To apply the Apache License to your work, attach the following 181 | boilerplate notice, with the fields enclosed by brackets "[]" 182 | replaced with your own identifying information. (Don't include 183 | the brackets!) The text should be enclosed in the appropriate 184 | comment syntax for the file format. We also recommend that a 185 | file or class name and description of purpose be included on the 186 | same "printed page" as the copyright notice for easier 187 | identification within third-party archives. 188 | 189 | Copyright [yyyy] [name of copyright owner] 190 | 191 | Licensed under the Apache License, Version 2.0 (the "License"); 192 | you may not use this file except in compliance with the License. 193 | You may obtain a copy of the License at 194 | 195 | http://www.apache.org/licenses/LICENSE-2.0 196 | 197 | Unless required by applicable law or agreed to in writing, software 198 | distributed under the License is distributed on an "AS IS" BASIS, 199 | WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 200 | See the License for the specific language governing permissions and 201 | limitations under the License. 202 | -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- 1 | # Awesome-Distribution-Shift 2 | A curated list of Distribution Shift papers/articles and recent advancements. 3 | 4 | Data distribution shift refers to the phenomenon in supervised learning when the data a model works with changes over time, which causes this model’s predictions to become less accurate as time passes. The distribution of the data the model is trained on is called the source distribution. This repo contains a curated list of Distribution Shift papers/articles and recent advancements in Machine learning. 5 |

6 | 7 | [![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg)](https://github.com/sindresorhus/awesome) 8 | [![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com) 9 | [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT) 10 | 11 | 12 |

13 | 14 | 15 | 16 | ##### Table of Contents 17 | 18 | 1. [Papers](#Distribution-Shift-papers) 19 | 2. [Code](#Code) 20 | 3. [datasets](#Datasets) 21 | 4. [Tutorials](#Tutorials) 22 | 5. [Researchers](#Researchers) 23 | 24 | 25 | ## Papers 26 | 27 | - **Enhancing Model Robustness and Fairness with Causality: A Regularization Approach** 28 | - [[Paper]](https://aclanthology.org/2021.cinlp-1.3.pdf) 29 | - **Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification** 30 | - [[Paper]](https://aclanthology.org/2021.findings-acl.294.pdf) 31 | - **[2001.08103] Secure and Robust Machine Learning for Healthcare: A Survey** 32 | - [[Paper]](https://arxiv.org/abs/2001.08103) 33 | - **[2103.08291] Robust Machine Learning in Critical Care -- Software Engineering and Medical Perspectives** 34 | - [[Paper]](https://arxiv.org/abs/2103.08291) 35 | - **[2108.00402] Style Curriculum Learning for Robust Medical Image Segmentation** 36 | - [[Paper]](https://arxiv.org/abs/2108.00402) 37 | - **[2108.12242] Deep learning models are not robust against noise in clinical text** 38 | - [[Paper]](https://arxiv.org/abs/2108.12242) 39 | - **[2210.00589] Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective** 40 | - [[Paper]](https://arxiv.org/abs/2210.00589) 41 | - **[2209.15042] Generalizability of Adversarial Robustness Under Distribution Shifts** 42 | - [[Paper]](https://arxiv.org/abs/2209.15042) 43 | - **[2209.09423] Fairness and robustness in anti-causal prediction** 44 | - [[Paper]](https://arxiv.org/abs/2209.09423) 45 | - **[2209.09631] De-Identification of French Unstructured Clinical Notes for Machine Learning Tasks** 46 | - [[Paper]](https://arxiv.org/abs/2209.09631) 47 | - **[2207.00769] Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift** 48 | - [[Paper]](https://arxiv.org/abs/2207.00769) 49 | - **Performance deterioration of deep neural networks for lesion classification in mammography due to distribution shift: an analysis based on artificially created distribution shift** 50 | - [[Paper]](https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11314/2551346/Performance-deterioration-of-deep-neural-networks-for-lesion-classification-in/10.1117/12.2551346.short?SSO=1) 51 | - **[2109.01668] How Reliable Are Out-of-Distribution Generalization Methods for Medical Image Segmentation?** 52 | - [[Paper]](https://arxiv.org/abs/2109.01668) 53 | - **[1910.13681] The Domain Shift Problem of Medical Image Segmentation and Vendor-Adaptation by Unet-GAN** 54 | - [[Paper]](https://arxiv.org/abs/1910.13681) 55 | - **Secure and Robust Machine Learning for Healthcare: A Survey** 56 | - [[Paper]](https://core.ac.uk/download/pdf/328760438.pdf) 57 | - **AIMI Research Meeting: Rethink Robustness of Deep Learning Models for Medical Image Analysis - Yuyin Zhou, PhD** 58 | - [[Paper]](https://aimi.stanford.edu/events/research-meeting/aimi-research-meeting-rethink-robustness-deep-learning-models-medical-image) 59 | - **Identification of robust deep neural network models of longitudinal clinical measurements** 60 | - [[Paper]](https://www.nature.com/articles/s41746-022-00651-4) 61 | - **Robustness of AI-based prognostic and systems health management - ScienceDirect** 62 | - [[Paper]](https://www.sciencedirect.com/science/article/abs/pii/S1367578821000195) 63 | - **The impact of domain shift on the calibration of fine-tuned models** 64 | - [[Paper]](https://openreview.net/forum?id=dZ7MVojplmi) 65 | - **[2110.01955] Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks** 66 | - [[Paper]](https://arxiv.org/abs/2110.01955) 67 | - **agrawal20a.pdf** 68 | - [[Paper]](http://proceedings.mlr.press/v126/agrawal20a/agrawal20a.pdf) 69 | - **nestor19a.pdf** 70 | - [[Paper]](http://proceedings.mlr.press/v106/nestor19a/nestor19a.pdf) 71 | - **liu21f.pdf** 72 | - [[Paper]](http://proceedings.mlr.press/v139/liu21f/liu21f.pdf) 73 | - **cheng20a.pdf** 74 | - [[Paper]](http://proceedings.mlr.press/v121/cheng20a/cheng20a.pdf) 75 | - **EHR Foundation Models Improve Robustness in the Presence of Temporal Distribution Shift** 76 | - [[Paper]](https://www.medrxiv.org/content/10.1101/2022.04.15.22273900v1.full) 77 | - **Maintaining fairness across distribution shift: do we have viable solutions for real-world applications?** 78 | - [[Paper]](https://montrealethics.ai/maintaining-fairness-across-distribution-shift-do-we-have-viable-solutions-for-real-world-applications/) 79 | - **Characterizing the Value of Information in Medical Notes** 80 | - [[Paper]](https://aclanthology.org/2020.findings-emnlp.187.pdf) 81 | - **subbaswamy19a.pdf** 82 | - [[Paper]](http://proceedings.mlr.press/v89/subbaswamy19a/subbaswamy19a.pdf) 83 | - **Forecasting Patient Outcomes in Kidney Exchange** 84 | - [[Paper]](https://www.ijcai.org/proceedings/2022/0701.pdf) 85 | - **https://openreview.net/pdf?id=AVTfiZgV64X** 86 | - [[Paper]](https://openreview.net/pdf?id=AVTfiZgV64X) 87 | - **[1910.00199] Saliency is a Possible Red Herring When Diagnosing Poor Generalization** 88 | - [[Paper]](https://arxiv.org/abs/1910.00199) 89 | - **[2007.00644] Measuring Robustness to Natural Distribution Shifts in Image Classification** 90 | - [[Paper]](https://arxiv.org/abs/2007.00644) 91 | - **[2206.14467] Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionary** 92 | - [[Paper]](https://arxiv.org/abs/2206.14467) 93 | - **[2205.13723] DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical Images** 94 | - [[Paper]](https://arxiv.org/abs/2205.13723) 95 | - **[2203.06060] ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRI** 96 | - [[Paper]](https://arxiv.org/abs/2203.06060) 97 | - **[2112.13734] Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models** 98 | - [[Paper]](https://arxiv.org/abs/2112.13734) 99 | - **[2110.14019] Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection** 100 | - [[Paper]](https://arxiv.org/abs/2110.14019) 101 | - **[2110.09276] Natural Attribute-based Shift Detection** 102 | - [[Paper]](https://arxiv.org/abs/2110.09276) 103 | - **[2109.13230] The Impact of Domain Shift on Left and Right Ventricle Segmentation in Short Axis Cardiac MR Images** 104 | - [[Paper]](https://arxiv.org/abs/2109.13230) 105 | - **Adapting Event Extractors to Medical Data: Bridging the Covariate Shift** 106 | - [[Paper]](https://aclanthology.org/2021.eacl-main.258.pdf) 107 | - **Distinguishing Clinical Sentiment: The Importance of Domain Adaptation in Psychiatric Patient Health Records** 108 | - [[Paper]](https://aclanthology.org/W19-1915.pdf) 109 | - **2022.clinicalnlp-1.10.pdf** 110 | - [[Paper]](https://aclanthology.org/2022.clinicalnlp-1.10.pdf) 111 | - **Investigating the Challenges of Temporal Relation Extraction from Clinical Text** 112 | - [[Paper]](https://aclanthology.org/W18-5607.pdf) 113 | - **2022.findings-acl.192.pdf** 114 | - [[Paper]](https://aclanthology.org/2022.findings-acl.192.pdf) 115 | - **2022.findings-acl.18.pdf** 116 | - [[Paper]](https://aclanthology.org/2022.findings-acl.18.pdf) 117 | - **otles21a.pdf** 118 | - [[Paper]](https://proceedings.mlr.press/v149/otles21a/otles21a.pdf) 119 | - **pfisterer22a.pdf** 120 | - [[Paper]](https://proceedings.mlr.press/v174/pfisterer22a/pfisterer22a.pdf) 121 | - **caldas21a.pdf** 122 | - [[Paper]](https://proceedings.mlr.press/v149/caldas21a/caldas21a.pdf) 123 | - **zhang13d.pdf** 124 | - [[Paper]](http://proceedings.mlr.press/v28/zhang13d.pdf) 125 | - **Review for NeurIPS paper: What went wrong and when? Instance-wise feature importance for time-series black-box models** 126 | - [[Paper]](https://papers.nips.cc/paper/2020/file/08fa43588c2571ade19bc0fa5936e028-Review.html) 127 | - **08fa43588c2571ade19bc0fa5936e028-Paper.pdf** 128 | - [[Paper]](https://papers.nips.cc/paper/2020/file/08fa43588c2571ade19bc0fa5936e028-Paper.pdf) 129 | - **908075ea2c025c335f4865f7db427062-Paper.pdf** 130 | - [[Paper]](https://papers.nips.cc/paper/2021/file/908075ea2c025c335f4865f7db427062-Paper.pdf) 131 | - **Domain Generalization via Model-Agnostic Learning of Semantic Features** 132 | - [[Paper]](https://proceedings.neurips.cc/paper/2019/file/2974788b53f73e7950e8aa49f3a306db-Paper.pdf) 133 | - **[2208.03392] Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directions** 134 | - [[Paper]](https://arxiv.org/abs/2208.03392) 135 | - **pdf** 136 | - [[Paper]](https://openreview.net/pdf?id=o20_NVA92tK) 137 | - **Adapting on the Fly to Test Time Distribution Shift – The Berkeley Artificial Intelligence Research Blog** 138 | - [[Paper]](https://bair.berkeley.edu/blog/2020/11/05/arm/) 139 | - **Estimating Generalization under Distribution Shifts via Domain-Invariant Representations** 140 | - [[Paper]](https://chingyaoc.github.io/generalization/) 141 | - **[2207.11486] Time Series Prediction under Distribution Shift using Differentiable Forgetting** 142 | - [[Paper]](https://arxiv.org/abs/2207.11486) 143 | - **https://www.ml.cmu.edu/research/phd-dissertation-pdfs/yw4_phd_ml_2021.pdf** 144 | - [[Paper]](https://www.ml.cmu.edu/research/phd-dissertation-pdfs/yw4_phd_ml_2021.pdf) 145 | - **statistics - Distribution Shift vs Transfer Learning - Data Science Stack Exchange** 146 | - [[Paper]](https://datascience.stackexchange.com/questions/103762/distribution-shift-vs-transfer-learning) 147 | - **Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift** 148 | - [[Paper]](https://proceedings.neurips.cc/paper/2019/file/846c260d715e5b854ffad5f70a516c88-Paper.pdf) 149 | - **[PDF] A Fine-Grained Analysis on Distribution Shift** 150 | - [[Paper]](https://www.semanticscholar.org/reader/0e845ef0a3ae71bd32a6954fafe0702d0f0f033f) 151 | - **The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization** 152 | - [[Paper]](https://openaccess.thecvf.com/content/ICCV2021/papers/Hendrycks_The_Many_Faces_of_Robustness_A_Critical_Analysis_of_Out-of-Distribution_ICCV_2021_paper.pdf) 153 | - **4.7. Environment and Distribution Shift — Dive into Deep Learning 1.0.0-alpha1.post0 documentation** 154 | - [[Paper]](https://d2l.ai/chapter_linear-classification/environment-and-distribution-shift.html) 155 | - **[2207.00476] Online Reflective Learning for Robust Medical Image Segmentation** 156 | - [[Paper]](https://arxiv.org/abs/2207.00476) 157 | - **[2207.01059] Identifying the Context Shift between Test Benchmarks and Production Data** 158 | - [[Paper]](https://arxiv.org/abs/2207.01059) 159 | - **[2206.05498] A Review of Causality for Learning Algorithms in Medical Image Analysis** 160 | - [[Paper]](https://arxiv.org/abs/2206.05498) 161 | - **[2206.08023] AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation** 162 | - [[Paper]](https://arxiv.org/abs/2206.08023) 163 | - **pdf** 164 | - [[Paper]](https://openreview.net/pdf?id=tv_pkmFzdC) 165 | - **darestani21a.pdf** 166 | - [[Paper]](http://proceedings.mlr.press/v139/darestani21a/darestani21a.pdf) 167 | - **Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data** 168 | - [[Paper]](https://openreview.net/pdf?id=o4JWdxYTjL8) 169 | - **pdf** 170 | - [[Paper]](https://openreview.net/pdf?id=hNMOSUxE8o6) 171 | - **Multi-Domain Ensembles for Domain Generalization** 172 | - [[Paper]](https://openreview.net/forum?id=mmlix0UucTh) 173 | - **Optimal Representations for Covariate Shifts** 174 | - [[Paper]](https://openreview.net/forum?id=de1kSNxv5BQ) 175 | - **Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration** 176 | - [[Paper]](https://openreview.net/forum?id=G9FkQ0ZIoZ) 177 | - **Investigating Shifts in GAN Output-Distributions** 178 | - [[Paper]](https://openreview.net/forum?id=HPOZLHaMxQo) 179 | - **Exploring Covariate and Concept Shift for Out-of-Distribution Detection** 180 | - [[Paper]](https://openreview.net/forum?id=3AWGg4CySNh) 181 | - **Unsupervised Attribute Alignment for Characterizing Distribution Shift** 182 | - [[Paper]](https://openreview.net/forum?id=Bk1hklAuZyh) 183 | - **BEDS-Bench: Behavior of EHR-models under Distributional Shift - A Benchmark** 184 | - [[Paper]](https://openreview.net/forum?id=IKWYt4w1uDp) 185 | - **How Does Contrastive Pre-training Connect Disparate Domains?** 186 | - [[Paper]](https://openreview.net/forum?id=ZKCw3atVfsy) 187 | - **Ensembles and Cocktails: Robust Finetuning for Natural Language Generation** 188 | - [[Paper]](https://openreview.net/forum?id=qXucB21w1C3) 189 | - **Distribution Shift in Airline Customer Behavior during COVID-19** 190 | - [[Paper]](https://openreview.net/forum?id=ZJUJ9M2vZIn) 191 | - **PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures** 192 | - [[Paper]](https://openreview.net/forum?id=WeUg_KpkFtt) 193 | - **Avoiding Spurious Correlations: Bridging Theory and Practice** 194 | - [[Paper]](https://openreview.net/forum?id=xifR-LmUHC7) 195 | - **MEMO: Test Time Robustness via Adaptation and Augmentation** 196 | - [[Paper]](https://openreview.net/forum?id=vn74m_tWu8O) 197 | - **Understanding Post-hoc Adaptation for Improving Subgroup Robustness** 198 | - [[Paper]](https://openreview.net/forum?id=UmMqvN9Aid-) 199 | - **Diurnal or Nocturnal? Federated Learning from Periodically Shifting Distributions** 200 | - [[Paper]](https://openreview.net/forum?id=WRmTnEOk0E) 201 | - **An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters** 202 | - [[Paper]](https://openreview.net/forum?id=2st0AzxC3mh) 203 | - **Maximum Mean Discrepancy for Generalization in the Presence of Distribution and Missingness Shift** 204 | - [[Paper]](https://openreview.net/forum?id=U23Q46ZqZ-T) 205 | - **An Empirical Study of Pre-trained Vision Models on Out-of-distribution Generalization** 206 | - [[Paper]](https://openreview.net/forum?id=z-LBrGmZaNs) 207 | - **Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift** 208 | - [[Paper]](https://openreview.net/forum?id=311QRRkfrep) 209 | - **A benchmark with decomposed distribution shifts for 360 monocular depth estimation** 210 | - [[Paper]](https://openreview.net/forum?id=6ksR7XSRuGB) 211 | - **Leveraging Unlabeled Data to Predict Out-of-Distribution Performance** 212 | - [[Paper]](https://openreview.net/forum?id=wcrff7Gh0RR) 213 | - **Quantifying and Alleviating Distribution Shifts in Foundation Models on Review Classification** 214 | - [[Paper]](https://openreview.net/forum?id=OG78-TuPcvL) 215 | - **A fine-grained analysis of robustness to distribution shifts** 216 | - [[Paper]](https://openreview.net/forum?id=AVTfiZgV64X) 217 | - **A Closer Look at Distribution Shifts and Out-of-Distribution Generalization on Graphs** 218 | - [[Paper]](https://openreview.net/forum?id=XvgPGWazqRH) 219 | - **Is Importance Weighting Incompatible with Interpolating Classifiers?** 220 | - [[Paper]](https://openreview.net/forum?id=pEhpLxVsd03) 221 | - **Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks** 222 | - [[Paper]](https://openreview.net/forum?id=uJ2_JTpVCvc) 223 | - **A Benchmark for Text Quantification Learning Under Real-World Temporal Distribution Shift** 224 | - [[Paper]](https://openreview.net/forum?id=MndqjaCwQX) 225 | - **MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts** 226 | - [[Paper]](https://openreview.net/forum?id=MTex8qKavoS) 227 | - **[2112.13885] MedShift: identifying shift data for medical dataset curation** 228 | - [[Paper]](https://arxiv.org/abs/2112.13885) 229 | - **[2207.00769] Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift** 230 | - [[Paper]](https://arxiv.org/abs/2207.00769) 231 | - **[2207.05796] Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction** 232 | - [[Paper]](https://arxiv.org/abs/2207.05796) 233 | - **[2206.15274] Exposing and addressing the fragility of neural networks in digital pathology** 234 | - [[Paper]](https://arxiv.org/abs/2206.15274) 235 | - **[2205.09723] Robust and Efficient Medical Imaging with Self-Supervision** 236 | - [[Paper]](https://arxiv.org/abs/2205.09723) 237 | - **[2208.03217] Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation** 238 | - [[Paper]](https://arxiv.org/abs/2208.03217) 239 | - **[2203.05574] On-the-Fly Test-time Adaptation for Medical Image Segmentation** 240 | - [[Paper]](https://arxiv.org/abs/2203.05574) 241 | - **[2202.02833] CheXstray: Real-time Multi-Modal Data Concordance for Drift Detection in Medical Imaging AI** 242 | - [[Paper]](https://arxiv.org/abs/2202.02833) 243 | - **[2202.05271] A Field of Experts Prior for Adapting Neural Networks at Test Time** 244 | - [[Paper]](https://arxiv.org/abs/2202.05271) 245 | - **[2201.07317] A Privacy-Preserving Unsupervised Domain Adaptation Framework for Clinical Text Analysis** 246 | - [[Paper]](https://arxiv.org/abs/2201.07317) 247 | - **[2110.06866] Bayesian logistic regression for online recalibration and revision of risk prediction models with performance guarantees** 248 | - [[Paper]](https://arxiv.org/abs/2110.06866) 249 | - **[2107.14317] Temporal Dependencies in Feature Importance for Time Series Predictions** 250 | - [[Paper]](https://arxiv.org/abs/2107.14317) 251 | - **Analysis of Machine Learning Models Predicting Quality of Life for Cancer Patients** 252 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3444757.3485103) 253 | - **CSUR5405-111** 254 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3453444) 255 | - **Data Distribution Shifts and Monitoring** 256 | - [[Paper]](https://huyenchip.com/2022/02/07/data-distribution-shifts-and-monitoring.html) 257 | - **Shifting the distribution** 258 | - [[Paper]](https://academic.oup.com/book/9251/chapter-abstract/155945428?redirectedFrom=fulltext) 259 | - **Principles for Tackling Distribution Shift: Pessimism, Adaptation, and Anticipation - YouTube** 260 | - [[Paper]](https://www.youtube.com/watch?v=QKBh6TmvBaw) 261 | - **Zachary C. Lipton: Deep Learning Under Distribution Shift - YouTube** 262 | - [[Paper]](https://www.youtube.com/watch?v=WhpZKIra-FQ) 263 | - **Preventing dataset shift from breaking machine-learning biomarkers** 264 | - [[Paper]](https://hal.archives-ouvertes.fr/hal-03293375/file/main.pdf) 265 | - **pdf** 266 | - [[Paper]](https://openreview.net/pdf?id=6h14cMLgb5q) 267 | - **pdf** 268 | - [[Paper]](https://openreview.net/pdf?id=1oEvY1a67c1) 269 | - **How robust are pre-trained models to distribution shift?** 270 | - [[Paper]](https://openreview.net/pdf?id=zKDcZBVVEWm) 271 | - **[1911.00677] Fairness Violations and Mitigation under Covariate Shift** 272 | - [[Paper]](https://arxiv.org/abs/1911.00677) 273 | - **f9a2ae9ee8021aeb70a8f2deeab247a324b8200e.pdf** 274 | - [[Paper]](https://openreview.net/pdf/f9a2ae9ee8021aeb70a8f2deeab247a324b8200e.pdf) 275 | - **attachment** 276 | - [[Paper]](https://openreview.net/attachment?id=kiWRlrbVzSM&name=supplementary_material) 277 | - **pdf** 278 | - [[Paper]](https://openreview.net/pdf?id=Ro_zAjZppv) 279 | - **towards-explaining-image-based-shifts.pdf** 280 | - [[Paper]](https://www.seankulinski.com/publication/towards-explaining-image-based-shifts/towards-explaining-image-based-shifts.pdf) 281 | - **pdf** 282 | - [[Paper]](https://openreview.net/pdf?id=FQOC5u-1egI) 283 | - **pdf** 284 | - [[Paper]](https://openreview.net/pdf?id=Bk1hklAuZyh) 285 | - **[2110.11328] A Fine-Grained Analysis on Distribution Shift** 286 | - [[Paper]](https://arxiv.org/abs/2110.11328) 287 | - **[2205.12753] An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation** 288 | - [[Paper]](https://arxiv.org/abs/2205.12753) 289 | - **[2202.01034] Maintaining fairness across distribution shift: do we have viable solutions for real-world applications?** 290 | - [[Paper]](https://arxiv.org/abs/2202.01034) 291 | - **[2207.05796] Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction** 292 | - [[Paper]](https://arxiv.org/abs/2207.05796) 293 | - **EHR Foundation Models Improve Robustness in the Presence of Temporal Distribution Shift** 294 | - [[Paper]](https://www.medrxiv.org/content/10.1101/2022.04.15.22273900v1.full.pdf) 295 | - **SOoD: Self-Supervised Out-of-Distribution Detection Under Domain Shift for Multi-Class Colorectal Cancer Tissue Types** 296 | - [[Paper]](https://openaccess.thecvf.com/content/ICCV2021W/CVAMD/papers/Bozorgtabar_SOoD_Self-Supervised_Out-of-Distribution_Detection_Under_Domain_Shift_for_Multi-Class_Colorectal_ICCVW_2021_paper.pdf) 297 | - **subbaswamy21a.pdf** 298 | - [[Paper]](http://proceedings.mlr.press/v130/subbaswamy21a/subbaswamy21a.pdf) 299 | - **machine learning - Difference between distribution shift and data shift, concept drift and model drift - Cross Validated** 300 | - [[Paper]](https://stats.stackexchange.com/questions/548405/difference-between-distribution-shift-and-data-shift-concept-drift-and-model-dr) 301 | - **Understanding Dataset Shift. How to make sure your models are not…** 302 | - [[Paper]](https://towardsdatascience.com/understanding-dataset-shift-f2a5a262a766) 303 | - **Distribution Shift Framework** 304 | - [[Paper]](https://www.deepmind.com/open-source/distribution-shift-framework) 305 | - **4.7. Environment and Distribution Shift — Dive into Deep Learning 1.0.0-alpha1.post0 documentation** 306 | - [[Paper]](https://d2l.ai/chapter_linear-classification/environment-and-distribution-shift.html) 307 | - **https://www.ml.cmu.edu/research/phd-dissertation-pdfs/yw4_phd_ml_2021.pdf** 308 | - [[Paper]](https://www.ml.cmu.edu/research/phd-dissertation-pdfs/yw4_phd_ml_2021.pdf) 309 | - **Mechanical MNIST – Distribution Shift** 310 | - [[Paper]](https://open.bu.edu/handle/2144/44485) 311 | - **microsoft/distribution-shift-latent-representations** 312 | - [[Paper]](https://github.com/microsoft/distribution-shift-latent-representations) 313 | - **NeurIPS DistShift Workshop 2021** 314 | - [[Paper]](https://sites.google.com/view/distshift2021) 315 | - **Types of Out-of-Distribution Texts and How to Detect Them** 316 | - [[Paper]](https://aclanthology.org/2021.emnlp-main.835.pdf) 317 | - **Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction** 318 | - [[Paper]](https://aclanthology.org/D19-1397.pdf) 319 | - **To Annotate or Not? Predicting Performance Drop under Domain Shift** 320 | - [[Paper]](https://aclanthology.org/D19-1222.pdf) 321 | - **2022.acl-long.223.pdf** 322 | - [[Paper]](https://aclanthology.org/2022.acl-long.223.pdf) 323 | - **2022.repl4nlp-1.1.pdf** 324 | - [[Paper]](https://aclanthology.org/2022.repl4nlp-1.1.pdf) 325 | - **2022.findings-acl.68.pdf** 326 | - [[Paper]](https://aclanthology.org/2022.findings-acl.68.pdf) 327 | - **2022.acl-long.74.pdf** 328 | - [[Paper]](https://aclanthology.org/2022.acl-long.74.pdf) 329 | - **2022.naacl-main.339.pdf** 330 | - [[Paper]](https://aclanthology.org/2022.naacl-main.339.pdf) 331 | - **[2103.17171] Spectral decoupling allows training transferable neural networks in medical imaging** 332 | - [[Paper]](https://arxiv.org/abs/2103.17171) 333 | - **[2102.08660] CheXternal: Generalization of Deep Learning Models for Chest X-ray Interpretation to Photos of Chest X-rays and External Clinical Settings** 334 | - [[Paper]](https://arxiv.org/abs/2102.08660) 335 | - **[2012.10564] Computer-aided abnormality detection in chest radiographs in a clinical setting via domain-adaptation** 336 | - [[Paper]](https://arxiv.org/abs/2012.10564) 337 | - **[2011.11750] Federated Semi-Supervised Learning for COVID Region Segmentation in Chest CT using Multi-National Data from China, Italy, Japan** 338 | - [[Paper]](https://arxiv.org/abs/2011.11750) 339 | - **[2010.06667] Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings** 340 | - [[Paper]](https://arxiv.org/abs/2010.06667) 341 | - **[2007.02035] Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains** 342 | - [[Paper]](https://arxiv.org/abs/2007.02035) 343 | - **[2006.00327] Probabilistic self-learning framework for Low-dose CT Denoising** 344 | - [[Paper]](https://arxiv.org/abs/2006.00327) 345 | - **Metric Learning in Optimal Transport for Domain Adaptation** 346 | - [[Paper]](https://www.ijcai.org/proceedings/2020/0299.pdf) 347 | - **pdf** 348 | - [[Paper]](https://openreview.net/pdf?id=hNMOSUxE8o6) 349 | - **pdf** 350 | - [[Paper]](https://openreview.net/pdf?id=F9ENmZABB0) 351 | - **pdf** 352 | - [[Paper]](https://openreview.net/pdf?id=aZgiUNye2Cz) 353 | - **pdf** 354 | - [[Paper]](https://openreview.net/pdf?id=MJgzr6dQPvl) 355 | - **pdf** 356 | - [[Paper]](https://openreview.net/pdf?id=Bx41qYMdw83) 357 | - **pdf** 358 | - [[Paper]](https://openreview.net/pdf?id=L3gKhQ2NZyI) 359 | - **pdf** 360 | - [[Paper]](https://openreview.net/pdf?id=W0fKtUQgcRR) 361 | - **pdf** 362 | - [[Paper]](https://openreview.net/pdf?id=bAO-2cGNX_j) 363 | - **pdf** 364 | - [[Paper]](https://openreview.net/pdf?id=2EhHKKXMbG0) 365 | - **[2202.10808] Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks** 366 | - [[Paper]](https://arxiv.org/abs/2202.10808) 367 | - **[2207.11486] Time Series Prediction under Distribution Shift using Differentiable Forgetting** 368 | - [[Paper]](https://arxiv.org/abs/2207.11486) 369 | - **[2204.10049] On Distribution Shift in Learning-based Bug Detectors** 370 | - [[Paper]](https://arxiv.org/abs/2204.10049) 371 | - **[2206.00129] Fairness Transferability Subject to Bounded Distribution Shift** 372 | - [[Paper]](https://arxiv.org/abs/2206.00129) 373 | - **[2208.06604] Combating Label Distribution Shift for Active Domain Adaptation** 374 | - [[Paper]](https://arxiv.org/abs/2208.06604) 375 | - **[2209.11459] TeST: Test-time Self-Training under Distribution Shift** 376 | - [[Paper]](https://arxiv.org/abs/2209.11459) 377 | - **[2202.06523] MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts** 378 | - [[Paper]](https://arxiv.org/abs/2202.06523) 379 | - **[2207.05796] Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction** 380 | - [[Paper]](https://arxiv.org/abs/2207.05796) 381 | - **[2206.13089] Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift** 382 | - [[Paper]](https://arxiv.org/abs/2206.13089) 383 | - **[2210.00084] Contrastive Graph Few-Shot Learning** 384 | - [[Paper]](https://arxiv.org/abs/2210.00084) 385 | - **[2210.01360] Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks** 386 | - [[Paper]](https://arxiv.org/abs/2210.01360) 387 | - **[2210.01979] GAPX: Generalized Autoregressive Paraphrase-Identification X** 388 | - [[Paper]](https://arxiv.org/abs/2210.01979) 389 | - **[2210.03103] Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content!** 390 | - [[Paper]](https://arxiv.org/abs/2210.03103) 391 | - **[2210.01930] Benchmarking Learnt Radio Localisation under Distribution Shift** 392 | - [[Paper]](https://arxiv.org/abs/2210.01930) 393 | - **[2209.01332] Class-Specific Channel Attention for Few-Shot Learning** 394 | - [[Paper]](https://arxiv.org/abs/2209.01332) 395 | - **[2209.01321] Deep Stable Representation Learning on Electronic Health Records** 396 | - [[Paper]](https://arxiv.org/abs/2209.01321) 397 | - **[2209.15177] Domain Generalization -- A Causal Perspective** 398 | - [[Paper]](https://arxiv.org/abs/2209.15177) 399 | - **[2209.03620] Black-Box Audits for Group Distribution Shifts** 400 | - [[Paper]](https://arxiv.org/abs/2209.03620) 401 | - **[2209.05706] Non-Parametric Temporal Adaptation for Social Media Topic Classification** 402 | - [[Paper]](https://arxiv.org/abs/2209.05706) 403 | - **[2209.05779] Test-Time Adaptation with Principal Component Analysis** 404 | - [[Paper]](https://arxiv.org/abs/2209.05779) 405 | - **Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual** 406 | - [[Paper]](https://aclanthology.org/D19-6115.pdf) 407 | - **2022.findings-naacl.13.pdf** 408 | - [[Paper]](https://aclanthology.org/2022.findings-naacl.13.pdf) 409 | - **2022.acl-long.256.pdf** 410 | - [[Paper]](https://aclanthology.org/2022.acl-long.256.pdf) 411 | - **2022.naacl-srw.6.pdf** 412 | - [[Paper]](https://aclanthology.org/2022.naacl-srw.6.pdf) 413 | - **Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing** 414 | - [[Paper]](https://proceedings.mlr.press/v162/darestani22a/darestani22a.pdf) 415 | - **zhou21g.pdf** 416 | - [[Paper]](http://proceedings.mlr.press/v139/zhou21g/zhou21g.pdf) 417 | - **he22a.pdf** 418 | - [[Paper]](https://proceedings.mlr.press/v162/he22a/he22a.pdf) 419 | - **Estimating Generalization under Distribution Shifts via Domain-Invariant Representations** 420 | - [[Paper]](http://proceedings.mlr.press/v119/chuang20a/chuang20a.pdf) 421 | - **LTF: A Label Transformation Framework for Correcting Target Shift** 422 | - [[Paper]](http://proceedings.mlr.press/v119/guo20d/guo20d.pdf) 423 | - **07ac7cd13fd0eb1654ccdbd222b81437-Paper.pdf** 424 | - [[Paper]](https://papers.nips.cc/paper/2021/file/07ac7cd13fd0eb1654ccdbd222b81437-Paper.pdf) 425 | - **8b9e7ab295e87570551db122a04c6f7c-Paper.pdf** 426 | - [[Paper]](https://papers.nips.cc/paper/2020/file/8b9e7ab295e87570551db122a04c6f7c-Paper.pdf) 427 | - **d1f255a373a3cef72e03aa9d980c7eca-Paper.pdf** 428 | - [[Paper]](https://papers.nips.cc/paper/2021/file/d1f255a373a3cef72e03aa9d980c7eca-Paper.pdf) 429 | - **219e052492f4008818b8adb6366c7ed6-Paper.pdf** 430 | - [[Paper]](https://papers.nips.cc/paper/2020/file/219e052492f4008818b8adb6366c7ed6-Paper.pdf) 431 | - **Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle** 432 | - [[Paper]](https://proceedings.neurips.cc/paper/2019/file/3d8e03e8b133b16f13a586f0c01b6866-Paper.pdf) 433 | - **f5e536083a438cec5b64a4954abc17f1-Paper.pdf** 434 | - [[Paper]](https://papers.nips.cc/paper/2020/file/f5e536083a438cec5b64a4954abc17f1-Paper.pdf) 435 | - **Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions** 436 | - [[Paper]](https://proceedings.neurips.cc/paper/2018/file/39e98420b5e98bfbdc8a619bef7b8f61-Paper.pdf) 437 | - **dfbfa7ddcfffeb581f50edcf9a0204bb-Paper.pdf** 438 | - [[Paper]](https://papers.nips.cc/paper/2020/file/dfbfa7ddcfffeb581f50edcf9a0204bb-Paper.pdf) 439 | - **https://www.ijcai.org/Proceedings/15/Papers/147.pdf** 440 | - [[Paper]](https://www.ijcai.org/Proceedings/15/Papers/147.pdf) 441 | - **https://www.ijcai.org/proceedings/2022/0232.pdf** 442 | - [[Paper]](https://www.ijcai.org/proceedings/2022/0232.pdf) 443 | - **https://www.ijcai.org/proceedings/2022/0484.pdf** 444 | - [[Paper]](https://www.ijcai.org/proceedings/2022/0484.pdf) 445 | - **https://www.ijcai.org/proceedings/2022/0595.pdf** 446 | - [[Paper]](https://www.ijcai.org/proceedings/2022/0595.pdf) 447 | - **https://www.ijcai.org/proceedings/2021/0644.pdf** 448 | - [[Paper]](https://www.ijcai.org/proceedings/2021/0644.pdf) 449 | - **https://www.ijcai.org/proceedings/2022/0392.pdf** 450 | - [[Paper]](https://www.ijcai.org/proceedings/2022/0392.pdf) 451 | - **https://www.ijcai.org/proceedings/2022/0501.pdf** 452 | - [[Paper]](https://www.ijcai.org/proceedings/2022/0501.pdf) 453 | - **https://www.ijcai.org/proceedings/2022/0514.pdf** 454 | - [[Paper]](https://www.ijcai.org/proceedings/2022/0514.pdf) 455 | - **https://www.ijcai.org/proceedings/2021/0367.pdf** 456 | - [[Paper]](https://www.ijcai.org/proceedings/2021/0367.pdf) 457 | - **https://www.ijcai.org/proceedings/2022/0240.pdf** 458 | - [[Paper]](https://www.ijcai.org/proceedings/2022/0240.pdf) 459 | - **https://openreview.net/pdf?id=Dl4LetuLdyK** 460 | - [[Paper]](https://openreview.net/pdf?id=Dl4LetuLdyK) 461 | - **https://openreview.net/pdf?id=BUQD1tJ2UwK** 462 | - [[Paper]](https://openreview.net/pdf?id=BUQD1tJ2UwK) 463 | - **e2d52448d36918c575fa79d88647ba66-Paper.pdf** 464 | - [[Paper]](https://proceedings.neurips.cc/paper/2020/file/e2d52448d36918c575fa79d88647ba66-Paper.pdf) 465 | - **fang22a.pdf** 466 | - [[Paper]](https://proceedings.mlr.press/v162/fang22a/fang22a.pdf) 467 | - **kang22a.pdf** 468 | - [[Paper]](https://proceedings.mlr.press/v162/kang22a/kang22a.pdf) 469 | - **zhao21b.pdf** 470 | - [[Paper]](http://proceedings.mlr.press/v130/zhao21b/zhao21b.pdf) 471 | - **yu22i.pdf** 472 | - [[Paper]](https://proceedings.mlr.press/v162/yu22i/yu22i.pdf) 473 | - **Can Autonomous Vehicles Identify, Recover From,and Adapt to Distribution Shifts?** 474 | - [[Paper]](http://proceedings.mlr.press/v119/filos20a/filos20a.pdf) 475 | - **d8330f857a17c53d217014ee776bfd50-Paper.pdf** 476 | - [[Paper]](https://papers.nips.cc/paper/2020/file/d8330f857a17c53d217014ee776bfd50-Paper.pdf) 477 | - **0d441de75945e5acbc865406fc9a2559-Paper.pdf** 478 | - [[Paper]](https://papers.nips.cc/paper/2021/file/0d441de75945e5acbc865406fc9a2559-Paper.pdf) 479 | - **73fed7fd472e502d8908794430511f4d-Paper.pdf** 480 | - [[Paper]](https://papers.nips.cc/paper/2021/file/73fed7fd472e502d8908794430511f4d-Paper.pdf) 481 | - **8420d359404024567b5aefda1231af24-Paper.pdf** 482 | - [[Paper]](https://papers.nips.cc/paper/2021/file/8420d359404024567b5aefda1231af24-Paper.pdf) 483 | - **621461af90cadfdaf0e8d4cc25129f91-Paper.pdf** 484 | - [[Paper]](https://proceedings.neurips.cc/paper/2019/file/621461af90cadfdaf0e8d4cc25129f91-Paper.pdf) 485 | - **[2209.08253] Mitigating Both Covariate and Conditional Shift for Domain Generalization** 486 | - [[Paper]](https://arxiv.org/abs/2209.08253) 487 | - **[2209.00652] Towards Optimization and Model Selection for Domain Generalization: A Mixup-guided Solution** 488 | - [[Paper]](https://arxiv.org/abs/2209.00652) 489 | - **[2209.01501] Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions** 490 | - [[Paper]](https://arxiv.org/abs/2209.01501) 491 | - **[2209.02408] Robustness and invariance properties of image classifiers** 492 | - [[Paper]](https://arxiv.org/abs/2209.02408) 493 | - **[2209.08745] Importance Tempering: Group Robustness for Overparameterized Models** 494 | - [[Paper]](https://arxiv.org/abs/2209.08745) 495 | - **RECORD: Resource Constrained Semi-Supervised Learning under Distribution Shift** 496 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3394486.3403214) 497 | - **Towards Reliable Multimodal Stress Detection under Distribution Shift** 498 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3461615.3486570) 499 | - **Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift** 500 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3485447.3512172) 501 | - **Active Model Adaptation Under Unknown Shift** 502 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3534678.3539262) 503 | - **Balance-Subsampled Stable Prediction Across Unknown Test Data** 504 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3477052) 505 | - **Focused Context Balancing for Robust Offline Policy Evaluation** 506 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3292500.3330852) 507 | - **3511598** 508 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3511598) 509 | - **A Critical Reassessment of the Saerens-Latinne-Decaestecker Algorithm for Posterior Probability Adjustment** 510 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3433164) 511 | - **Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making** 512 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3479552) 513 | - **Co-training Disentangled Domain Adaptation Network for Leveraging Popularity Bias in Recommenders** 514 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3477495.3531952) 515 | - **CausPref: Causal Preference Learning for Out-of-Distribution Recommendation** 516 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3485447.3511969) 517 | - **Off-Policy Actor-critic for Recommender Systems** 518 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3523227.3546758) 519 | - **HybridRepair: towards annotation-efficient repair for deep learning models** 520 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3533767.3534408) 521 | - **Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration** 522 | - [[Paper]](https://dl.acm.org/doi/pdf/10.5555/3535850.3535978) 523 | - **Neural Statistics for Click-Through Rate Prediction** 524 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3477495.3531762) 525 | - **Influence Function for Unbiased Recommendation** 526 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3397271.3401321) 527 | - **DCAF-BERT: A Distilled Cachable Adaptable Factorized Model For Improved Ads CTR Prediction** 528 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3487553.3524206) 529 | - **Making Adversarially-Trained Language Models Forget with Model Retraining: A Case Study on Hate Speech Detection** 530 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3487553.3524667) 531 | - **3455716.3455805** 532 | - [[Paper]](https://dl.acm.org/doi/pdf/10.5555/3455716.3455805) 533 | - **AdaRNN** 534 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3459637.3482315) 535 | - **Transfer String Kernel for Cross-Context DNA-Protein Binding Prediction** 536 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1109/TCBB.2016.2609918) 537 | - **Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling** 538 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3447548.3467086) 539 | - **A New Generation of Perspective API: Efficient Multilingual Character-level Transformers** 540 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3534678.3539147) 541 | - **Robust Self-Supervised Structural Graph Neural Network for Social Network Prediction** 542 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3485447.3512182) 543 | - **Stable Prediction across Unknown Environments** 544 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3219819.3220082) 545 | - **3460120.3484776** 546 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3460120.3484776) 547 | - **Fairness Violations and Mitigation under Covariate Shift** 548 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3442188.3445865) 549 | - **Quantifying the Performance of Adversarial Training on Language Models with Distribution Shifts** 550 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3494108.3522764) 551 | - **FedRS** 552 | - [[Paper]](https://dl.acm.org/doi/pdf/10.1145/3447548.3467254) 553 | - **[2208.02896] Interpretable Distribution Shift Detection using Optimal Transport** 554 | - [[Paper]](https://arxiv.org/abs/2208.02896) 555 | - **[2206.05480] CodeS: A Distribution Shift Benchmark Dataset for Source Code Learning** 556 | - [[Paper]](https://arxiv.org/abs/2206.05480) 557 | - **[2206.08871] How robust are pre-trained models to distribution shift?** 558 | - [[Paper]](https://arxiv.org/abs/2206.08871) 559 | - **[2207.08977] Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift** 560 | - [[Paper]](https://arxiv.org/abs/2207.08977) 561 | - **[2202.02339] Discovering Distribution Shifts using Latent Space Representations** 562 | - [[Paper]](https://arxiv.org/abs/2202.02339) 563 | - **[2207.04075] Models Out of Line: A Fourier Lens on Distribution Shift Robustness** 564 | - [[Paper]](https://arxiv.org/abs/2207.04075) 565 | -------------------------------------------------------------------------------- /images/data.txt: -------------------------------------------------------------------------------- 1 | demo 2 | -------------------------------------------------------------------------------- /images/dishit.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/monk1337/Awesome-Distribution-Shift/2f1646e381d33080bd20180486a830521a773981/images/dishit.png -------------------------------------------------------------------------------- /json_data.txt: -------------------------------------------------------------------------------- 1 | {'data': {'data': [{'title': 'Enhancing Model Robustness and Fairness with Causality: A Regularization Approach', 2 | 'paper': 'https://aclanthology.org/2021.cinlp-1.3.pdf'}, 3 | {'title': 'Does Robustness Improve Fairness? Approaching Fairness with Word Substitution Robustness Methods for Text Classification', 4 | 'paper': 'https://aclanthology.org/2021.findings-acl.294.pdf'}, 5 | {'title': 'agrawal20a.pdf', 6 | 'paper': 'http://proceedings.mlr.press/v126/agrawal20a/agrawal20a.pdf'}, 7 | {'title': 'nestor19a.pdf', 8 | 'paper': 'http://proceedings.mlr.press/v106/nestor19a/nestor19a.pdf'}, 9 | {'title': 'liu21f.pdf', 10 | 'paper': 'http://proceedings.mlr.press/v139/liu21f/liu21f.pdf'}, 11 | {'title': 'cheng20a.pdf', 12 | 'paper': 'http://proceedings.mlr.press/v121/cheng20a/cheng20a.pdf'}, 13 | {'title': 'EHR Foundation Models Improve Robustness in the Presence of Temporal Distribution Shift', 14 | 'paper': 'https://www.medrxiv.org/content/10.1101/2022.04.15.22273900v1.full'}, 15 | {'title': 'Maintaining fairness across distribution shift: do we have viable solutions for real-world applications?', 16 | 'paper': 'https://montrealethics.ai/maintaining-fairness-across-distribution-shift-do-we-have-viable-solutions-for-real-world-applications/'}, 17 | {'title': 'Characterizing the Value of Information in Medical Notes', 18 | 'paper': 'https://aclanthology.org/2020.findings-emnlp.187.pdf'}, 19 | {'title': 'subbaswamy19a.pdf', 20 | 'paper': 'http://proceedings.mlr.press/v89/subbaswamy19a/subbaswamy19a.pdf'}, 21 | {'title': 'Forecasting Patient Outcomes in Kidney Exchange', 22 | 'paper': 'https://www.ijcai.org/proceedings/2022/0701.pdf'}, 23 | {'title': 'https://openreview.net/pdf?id=AVTfiZgV64X', 24 | 'paper': 'https://openreview.net/pdf?id=AVTfiZgV64X'}, 25 | {'title': '[1910.00199] Saliency is a Possible Red Herring When Diagnosing Poor Generalization', 26 | 'paper': 'https://arxiv.org/abs/1910.00199'}, 27 | {'title': '[2007.00644] Measuring Robustness to Natural Distribution Shifts in Image Classification', 28 | 'paper': 'https://arxiv.org/abs/2007.00644'}, 29 | {'title': '[2206.14467] Single-domain Generalization in Medical Image Segmentation via Test-time Adaptation from Shape Dictionary', 30 | 'paper': 'https://arxiv.org/abs/2206.14467'}, 31 | {'title': '[2205.13723] DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical Images', 32 | 'paper': 'https://arxiv.org/abs/2205.13723'}, 33 | {'title': '[2203.06060] ROOD-MRI: Benchmarking the robustness of deep learning segmentation models to out-of-distribution and corrupted data in MRI', 34 | 'paper': 'https://arxiv.org/abs/2203.06060'}, 35 | {'title': '[2112.13734] Multi-Domain Balanced Sampling Improves Out-of-Distribution Generalization of Chest X-ray Pathology Prediction Models', 36 | 'paper': 'https://arxiv.org/abs/2112.13734'}, 37 | {'title': '[2110.14019] Reliable and Trustworthy Machine Learning for Health Using Dataset Shift Detection', 38 | 'paper': 'https://arxiv.org/abs/2110.14019'}, 39 | {'title': '[2110.09276] Natural Attribute-based Shift Detection', 40 | 'paper': 'https://arxiv.org/abs/2110.09276'}, 41 | {'title': '[2109.13230] The Impact of Domain Shift on Left and Right Ventricle Segmentation in Short Axis Cardiac MR Images', 42 | 'paper': 'https://arxiv.org/abs/2109.13230'}, 43 | {'title': 'Adapting Event Extractors to Medical Data: Bridging the Covariate Shift', 44 | 'paper': 'https://aclanthology.org/2021.eacl-main.258.pdf'}, 45 | {'title': 'Distinguishing Clinical Sentiment: The Importance of Domain Adaptation in Psychiatric Patient Health Records', 46 | 'paper': 'https://aclanthology.org/W19-1915.pdf'}, 47 | {'title': '2022.clinicalnlp-1.10.pdf', 48 | 'paper': 'https://aclanthology.org/2022.clinicalnlp-1.10.pdf'}, 49 | {'title': 'Investigating the Challenges of Temporal Relation Extraction from Clinical Text', 50 | 'paper': 'https://aclanthology.org/W18-5607.pdf'}, 51 | {'title': '2022.findings-acl.192.pdf', 52 | 'paper': 'https://aclanthology.org/2022.findings-acl.192.pdf'}, 53 | {'title': '2022.findings-acl.18.pdf', 54 | 'paper': 'https://aclanthology.org/2022.findings-acl.18.pdf'}, 55 | {'title': 'otles21a.pdf', 56 | 'paper': 'https://proceedings.mlr.press/v149/otles21a/otles21a.pdf'}, 57 | {'title': 'pfisterer22a.pdf', 58 | 'paper': 'https://proceedings.mlr.press/v174/pfisterer22a/pfisterer22a.pdf'}, 59 | {'title': 'caldas21a.pdf', 60 | 'paper': 'https://proceedings.mlr.press/v149/caldas21a/caldas21a.pdf'}, 61 | {'title': 'zhang13d.pdf', 62 | 'paper': 'http://proceedings.mlr.press/v28/zhang13d.pdf'}, 63 | {'title': 'Review for NeurIPS paper: What went wrong and when? Instance-wise feature importance for time-series black-box models', 64 | 'paper': 'https://papers.nips.cc/paper/2020/file/08fa43588c2571ade19bc0fa5936e028-Review.html'}, 65 | {'title': '08fa43588c2571ade19bc0fa5936e028-Paper.pdf', 66 | 'paper': 'https://papers.nips.cc/paper/2020/file/08fa43588c2571ade19bc0fa5936e028-Paper.pdf'}, 67 | {'title': '908075ea2c025c335f4865f7db427062-Paper.pdf', 68 | 'paper': 'https://papers.nips.cc/paper/2021/file/908075ea2c025c335f4865f7db427062-Paper.pdf'}, 69 | {'title': 'Domain Generalization via Model-Agnostic Learning of Semantic Features', 70 | 'paper': 'https://proceedings.neurips.cc/paper/2019/file/2974788b53f73e7950e8aa49f3a306db-Paper.pdf'}, 71 | {'title': '[2208.03392] Federated Learning for Medical Applications: A Taxonomy, Current Trends, Challenges, and Future Research Directions', 72 | 'paper': 'https://arxiv.org/abs/2208.03392'}, 73 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=o20_NVA92tK'}, 74 | {'title': 'Adapting on the Fly to Test Time Distribution Shift – The Berkeley Artificial Intelligence Research Blog', 75 | 'paper': 'https://bair.berkeley.edu/blog/2020/11/05/arm/'}, 76 | {'title': 'Estimating Generalization under Distribution Shifts via Domain-Invariant Representations', 77 | 'paper': 'https://chingyaoc.github.io/generalization/'}, 78 | {'title': '[2207.11486] Time Series Prediction under Distribution Shift using Differentiable Forgetting', 79 | 'paper': 'https://arxiv.org/abs/2207.11486'}, 80 | {'title': 'https://www.ml.cmu.edu/research/phd-dissertation-pdfs/yw4_phd_ml_2021.pdf', 81 | 'paper': 'https://www.ml.cmu.edu/research/phd-dissertation-pdfs/yw4_phd_ml_2021.pdf'}, 82 | {'title': 'statistics - Distribution Shift vs Transfer Learning - Data Science Stack Exchange', 83 | 'paper': 'https://datascience.stackexchange.com/questions/103762/distribution-shift-vs-transfer-learning'}, 84 | {'title': 'Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift', 85 | 'paper': 'https://proceedings.neurips.cc/paper/2019/file/846c260d715e5b854ffad5f70a516c88-Paper.pdf'}, 86 | {'title': '[PDF] A Fine-Grained Analysis on Distribution Shift', 87 | 'paper': 'https://www.semanticscholar.org/reader/0e845ef0a3ae71bd32a6954fafe0702d0f0f033f'}, 88 | {'title': 'The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization', 89 | 'paper': 'https://openaccess.thecvf.com/content/ICCV2021/papers/Hendrycks_The_Many_Faces_of_Robustness_A_Critical_Analysis_of_Out-of-Distribution_ICCV_2021_paper.pdf'}, 90 | {'title': '4.7. Environment and Distribution Shift — Dive into Deep Learning 1.0.0-alpha1.post0 documentation', 91 | 'paper': 'https://d2l.ai/chapter_linear-classification/environment-and-distribution-shift.html'}, 92 | {'title': '[2207.00476] Online Reflective Learning for Robust Medical Image Segmentation', 93 | 'paper': 'https://arxiv.org/abs/2207.00476'}, 94 | {'title': '[2207.01059] Identifying the Context Shift between Test Benchmarks and Production Data', 95 | 'paper': 'https://arxiv.org/abs/2207.01059'}, 96 | {'title': '[2206.05498] A Review of Causality for Learning Algorithms in Medical Image Analysis', 97 | 'paper': 'https://arxiv.org/abs/2206.05498'}, 98 | {'title': '[2206.08023] AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation', 99 | 'paper': 'https://arxiv.org/abs/2206.08023'}, 100 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=tv_pkmFzdC'}, 101 | {'title': 'darestani21a.pdf', 102 | 'paper': 'http://proceedings.mlr.press/v139/darestani21a/darestani21a.pdf'}, 103 | {'title': 'Conditional Synthetic Data Generation for Robust Machine Learning Applications with Limited Pandemic Data', 104 | 'paper': 'https://openreview.net/pdf?id=o4JWdxYTjL8'}, 105 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=hNMOSUxE8o6'}, 106 | {'title': '[2001.08103] Secure and Robust Machine Learning for Healthcare: A Survey', 107 | 'paper': 'https://arxiv.org/abs/2001.08103'}, 108 | {'title': '[2103.08291] Robust Machine Learning in Critical Care -- Software Engineering and Medical Perspectives', 109 | 'paper': 'https://arxiv.org/abs/2103.08291'}, 110 | {'title': '[2108.00402] Style Curriculum Learning for Robust Medical Image Segmentation', 111 | 'paper': 'https://arxiv.org/abs/2108.00402'}, 112 | {'title': '[2108.12242] Deep learning models are not robust against noise in clinical text', 113 | 'paper': 'https://arxiv.org/abs/2108.12242'}, 114 | {'title': "[2210.00589] Uncertainty estimations methods for a deep learning model to aid in clinical decision-making -- a clinician's perspective", 115 | 'paper': 'https://arxiv.org/abs/2210.00589'}, 116 | {'title': '[2209.15042] Generalizability of Adversarial Robustness Under Distribution Shifts', 117 | 'paper': 'https://arxiv.org/abs/2209.15042'}, 118 | {'title': '[2209.09423] Fairness and robustness in anti-causal prediction', 119 | 'paper': 'https://arxiv.org/abs/2209.09423'}, 120 | {'title': '[2209.09631] De-Identification of French Unstructured Clinical Notes for Machine Learning Tasks', 121 | 'paper': 'https://arxiv.org/abs/2209.09631'}, 122 | {'title': '[2207.00769] Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift', 123 | 'paper': 'https://arxiv.org/abs/2207.00769'}, 124 | {'title': 'Performance deterioration of deep neural networks for lesion classification in mammography due to distribution shift: an analysis based on artificially created distribution shift', 125 | 'paper': 'https://www.spiedigitallibrary.org/conference-proceedings-of-spie/11314/2551346/Performance-deterioration-of-deep-neural-networks-for-lesion-classification-in/10.1117/12.2551346.short?SSO=1'}, 126 | {'title': '[2109.01668] How Reliable Are Out-of-Distribution Generalization Methods for Medical Image Segmentation?', 127 | 'paper': 'https://arxiv.org/abs/2109.01668'}, 128 | {'title': '[1910.13681] The Domain Shift Problem of Medical Image Segmentation and Vendor-Adaptation by Unet-GAN', 129 | 'paper': 'https://arxiv.org/abs/1910.13681'}, 130 | {'title': 'Secure and Robust Machine Learning for Healthcare: A Survey', 131 | 'paper': 'https://core.ac.uk/download/pdf/328760438.pdf'}, 132 | {'title': 'AIMI Research Meeting: Rethink Robustness of Deep Learning Models for Medical Image Analysis - Yuyin Zhou, PhD', 133 | 'paper': 'https://aimi.stanford.edu/events/research-meeting/aimi-research-meeting-rethink-robustness-deep-learning-models-medical-image'}, 134 | {'title': 'Identification of robust deep neural network models of longitudinal clinical measurements', 135 | 'paper': 'https://www.nature.com/articles/s41746-022-00651-4'}, 136 | {'title': 'Robustness of AI-based prognostic and systems health management - ScienceDirect', 137 | 'paper': 'https://www.sciencedirect.com/science/article/abs/pii/S1367578821000195'}, 138 | {'title': 'The impact of domain shift on the calibration of fine-tuned models', 139 | 'paper': 'https://openreview.net/forum?id=dZ7MVojplmi'}, 140 | {'title': '[2110.01955] Distribution Mismatch Correction for Improved Robustness in Deep Neural Networks', 141 | 'paper': 'https://arxiv.org/abs/2110.01955'}, 142 | {'title': 'Multi-Domain Ensembles for Domain Generalization', 143 | 'paper': 'https://openreview.net/forum?id=mmlix0UucTh'}, 144 | {'title': 'Optimal Representations for Covariate Shifts', 145 | 'paper': 'https://openreview.net/forum?id=de1kSNxv5BQ'}, 146 | {'title': 'Fourier-Based Augmentations for Improved Robustness and Uncertainty Calibration', 147 | 'paper': 'https://openreview.net/forum?id=G9FkQ0ZIoZ'}, 148 | {'title': 'Investigating Shifts in GAN Output-Distributions', 149 | 'paper': 'https://openreview.net/forum?id=HPOZLHaMxQo'}, 150 | {'title': 'Exploring Covariate and Concept Shift for Out-of-Distribution Detection', 151 | 'paper': 'https://openreview.net/forum?id=3AWGg4CySNh'}, 152 | {'title': 'Unsupervised Attribute Alignment for Characterizing Distribution Shift', 153 | 'paper': 'https://openreview.net/forum?id=Bk1hklAuZyh'}, 154 | {'title': 'BEDS-Bench: Behavior of EHR-models under Distributional Shift - A Benchmark', 155 | 'paper': 'https://openreview.net/forum?id=IKWYt4w1uDp'}, 156 | {'title': 'How Does Contrastive Pre-training Connect Disparate Domains?', 157 | 'paper': 'https://openreview.net/forum?id=ZKCw3atVfsy'}, 158 | {'title': 'Ensembles and Cocktails: Robust Finetuning for Natural Language Generation', 159 | 'paper': 'https://openreview.net/forum?id=qXucB21w1C3'}, 160 | {'title': 'Distribution Shift in Airline Customer Behavior during COVID-19', 161 | 'paper': 'https://openreview.net/forum?id=ZJUJ9M2vZIn'}, 162 | {'title': 'PixMix: Dreamlike Pictures Comprehensively Improve Safety Measures', 163 | 'paper': 'https://openreview.net/forum?id=WeUg_KpkFtt'}, 164 | {'title': 'Avoiding Spurious Correlations: Bridging Theory and Practice', 165 | 'paper': 'https://openreview.net/forum?id=xifR-LmUHC7'}, 166 | {'title': 'MEMO: Test Time Robustness via Adaptation and Augmentation', 167 | 'paper': 'https://openreview.net/forum?id=vn74m_tWu8O'}, 168 | {'title': 'Understanding Post-hoc Adaptation for Improving Subgroup Robustness', 169 | 'paper': 'https://openreview.net/forum?id=UmMqvN9Aid-'}, 170 | {'title': 'Diurnal or Nocturnal? Federated Learning from Periodically Shifting Distributions', 171 | 'paper': 'https://openreview.net/forum?id=WRmTnEOk0E'}, 172 | {'title': 'An Empirical Investigation of Model-to-Model Distribution Shifts in Trained Convolutional Filters', 173 | 'paper': 'https://openreview.net/forum?id=2st0AzxC3mh'}, 174 | {'title': 'Maximum Mean Discrepancy for Generalization in the Presence of Distribution and Missingness Shift', 175 | 'paper': 'https://openreview.net/forum?id=U23Q46ZqZ-T'}, 176 | {'title': 'An Empirical Study of Pre-trained Vision Models on Out-of-distribution Generalization', 177 | 'paper': 'https://openreview.net/forum?id=z-LBrGmZaNs'}, 178 | {'title': 'Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift', 179 | 'paper': 'https://openreview.net/forum?id=311QRRkfrep'}, 180 | {'title': 'A benchmark with decomposed distribution shifts for 360 monocular depth estimation', 181 | 'paper': 'https://openreview.net/forum?id=6ksR7XSRuGB'}, 182 | {'title': 'Leveraging Unlabeled Data to Predict Out-of-Distribution Performance', 183 | 'paper': 'https://openreview.net/forum?id=wcrff7Gh0RR'}, 184 | {'title': 'Quantifying and Alleviating Distribution Shifts in Foundation Models on Review Classification', 185 | 'paper': 'https://openreview.net/forum?id=OG78-TuPcvL'}, 186 | {'title': 'A fine-grained analysis of robustness to distribution shifts', 187 | 'paper': 'https://openreview.net/forum?id=AVTfiZgV64X'}, 188 | {'title': 'A Closer Look at Distribution Shifts and Out-of-Distribution Generalization on Graphs', 189 | 'paper': 'https://openreview.net/forum?id=XvgPGWazqRH'}, 190 | {'title': 'Is Importance Weighting Incompatible with Interpolating Classifiers?', 191 | 'paper': 'https://openreview.net/forum?id=pEhpLxVsd03'}, 192 | {'title': 'Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Tasks', 193 | 'paper': 'https://openreview.net/forum?id=uJ2_JTpVCvc'}, 194 | {'title': 'A Benchmark for Text Quantification Learning Under Real-World Temporal Distribution Shift', 195 | 'paper': 'https://openreview.net/forum?id=MndqjaCwQX'}, 196 | {'title': 'MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts', 197 | 'paper': 'https://openreview.net/forum?id=MTex8qKavoS'}, 198 | {'title': '[2112.13885] MedShift: identifying shift data for medical dataset curation', 199 | 'paper': 'https://arxiv.org/abs/2112.13885'}, 200 | {'title': '[2207.00769] Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution Shift', 201 | 'paper': 'https://arxiv.org/abs/2207.00769'}, 202 | {'title': '[2207.05796] Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction', 203 | 'paper': 'https://arxiv.org/abs/2207.05796'}, 204 | {'title': '[2206.15274] Exposing and addressing the fragility of neural networks in digital pathology', 205 | 'paper': 'https://arxiv.org/abs/2206.15274'}, 206 | {'title': '[2205.09723] Robust and Efficient Medical Imaging with Self-Supervision', 207 | 'paper': 'https://arxiv.org/abs/2205.09723'}, 208 | {'title': '[2208.03217] Distance-based detection of out-of-distribution silent failures for Covid-19 lung lesion segmentation', 209 | 'paper': 'https://arxiv.org/abs/2208.03217'}, 210 | {'title': '[2203.05574] On-the-Fly Test-time Adaptation for Medical Image Segmentation', 211 | 'paper': 'https://arxiv.org/abs/2203.05574'}, 212 | {'title': '[2202.02833] CheXstray: Real-time Multi-Modal Data Concordance for Drift Detection in Medical Imaging AI', 213 | 'paper': 'https://arxiv.org/abs/2202.02833'}, 214 | {'title': '[2202.05271] A Field of Experts Prior for Adapting Neural Networks at Test Time', 215 | 'paper': 'https://arxiv.org/abs/2202.05271'}, 216 | {'title': '[2201.07317] A Privacy-Preserving Unsupervised Domain Adaptation Framework for Clinical Text Analysis', 217 | 'paper': 'https://arxiv.org/abs/2201.07317'}, 218 | {'title': '[2110.06866] Bayesian logistic regression for online recalibration and revision of risk prediction models with performance guarantees', 219 | 'paper': 'https://arxiv.org/abs/2110.06866'}, 220 | {'title': '[2107.14317] Temporal Dependencies in Feature Importance for Time Series Predictions', 221 | 'paper': 'https://arxiv.org/abs/2107.14317'}, 222 | {'title': 'Analysis of Machine Learning Models Predicting Quality of Life for Cancer Patients', 223 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3444757.3485103'}, 224 | {'title': 'CSUR5405-111', 225 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3453444'}, 226 | {'title': 'Data Distribution Shifts and Monitoring', 227 | 'paper': 'https://huyenchip.com/2022/02/07/data-distribution-shifts-and-monitoring.html'}, 228 | {'title': 'Shifting the distribution', 229 | 'paper': 'https://academic.oup.com/book/9251/chapter-abstract/155945428?redirectedFrom=fulltext'}, 230 | {'title': 'Principles for Tackling Distribution Shift: Pessimism, Adaptation, and Anticipation - YouTube', 231 | 'paper': 'https://www.youtube.com/watch?v=QKBh6TmvBaw'}, 232 | {'title': 'Zachary C. Lipton: Deep Learning Under Distribution Shift - YouTube', 233 | 'paper': 'https://www.youtube.com/watch?v=WhpZKIra-FQ'}, 234 | {'title': 'Preventing dataset shift from breaking machine-learning biomarkers', 235 | 'paper': 'https://hal.archives-ouvertes.fr/hal-03293375/file/main.pdf'}, 236 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=6h14cMLgb5q'}, 237 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=1oEvY1a67c1'}, 238 | {'title': 'How robust are pre-trained models to distribution shift?', 239 | 'paper': 'https://openreview.net/pdf?id=zKDcZBVVEWm'}, 240 | {'title': '[1911.00677] Fairness Violations and Mitigation under Covariate Shift', 241 | 'paper': 'https://arxiv.org/abs/1911.00677'}, 242 | {'title': 'f9a2ae9ee8021aeb70a8f2deeab247a324b8200e.pdf', 243 | 'paper': 'https://openreview.net/pdf/f9a2ae9ee8021aeb70a8f2deeab247a324b8200e.pdf'}, 244 | {'title': 'attachment', 245 | 'paper': 'https://openreview.net/attachment?id=kiWRlrbVzSM&name=supplementary_material'}, 246 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=Ro_zAjZppv'}, 247 | {'title': 'towards-explaining-image-based-shifts.pdf', 248 | 'paper': 'https://www.seankulinski.com/publication/towards-explaining-image-based-shifts/towards-explaining-image-based-shifts.pdf'}, 249 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=FQOC5u-1egI'}, 250 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=Bk1hklAuZyh'}, 251 | {'title': '[2110.11328] A Fine-Grained Analysis on Distribution Shift', 252 | 'paper': 'https://arxiv.org/abs/2110.11328'}, 253 | {'title': '[2205.12753] An Empirical Study on Distribution Shift Robustness From the Perspective of Pre-Training and Data Augmentation', 254 | 'paper': 'https://arxiv.org/abs/2205.12753'}, 255 | {'title': '[2202.01034] Maintaining fairness across distribution shift: do we have viable solutions for real-world applications?', 256 | 'paper': 'https://arxiv.org/abs/2202.01034'}, 257 | {'title': '[2207.05796] Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction', 258 | 'paper': 'https://arxiv.org/abs/2207.05796'}, 259 | {'title': 'EHR Foundation Models Improve Robustness in the Presence of Temporal Distribution Shift', 260 | 'paper': 'https://www.medrxiv.org/content/10.1101/2022.04.15.22273900v1.full.pdf'}, 261 | {'title': 'SOoD: Self-Supervised Out-of-Distribution Detection Under Domain Shift for Multi-Class Colorectal Cancer Tissue Types', 262 | 'paper': 'https://openaccess.thecvf.com/content/ICCV2021W/CVAMD/papers/Bozorgtabar_SOoD_Self-Supervised_Out-of-Distribution_Detection_Under_Domain_Shift_for_Multi-Class_Colorectal_ICCVW_2021_paper.pdf'}, 263 | {'title': 'subbaswamy21a.pdf', 264 | 'paper': 'http://proceedings.mlr.press/v130/subbaswamy21a/subbaswamy21a.pdf'}, 265 | {'title': 'machine learning - Difference between distribution shift and data shift, concept drift and model drift - Cross Validated', 266 | 'paper': 'https://stats.stackexchange.com/questions/548405/difference-between-distribution-shift-and-data-shift-concept-drift-and-model-dr'}, 267 | {'title': 'Understanding Dataset Shift. How to make sure your models are not…', 268 | 'paper': 'https://towardsdatascience.com/understanding-dataset-shift-f2a5a262a766'}, 269 | {'title': 'Distribution Shift Framework', 270 | 'paper': 'https://www.deepmind.com/open-source/distribution-shift-framework'}, 271 | {'title': '4.7. Environment and Distribution Shift — Dive into Deep Learning 1.0.0-alpha1.post0 documentation', 272 | 'paper': 'https://d2l.ai/chapter_linear-classification/environment-and-distribution-shift.html'}, 273 | {'title': 'https://www.ml.cmu.edu/research/phd-dissertation-pdfs/yw4_phd_ml_2021.pdf', 274 | 'paper': 'https://www.ml.cmu.edu/research/phd-dissertation-pdfs/yw4_phd_ml_2021.pdf'}, 275 | {'title': 'Mechanical MNIST – Distribution Shift', 276 | 'paper': 'https://open.bu.edu/handle/2144/44485'}, 277 | {'title': 'microsoft/distribution-shift-latent-representations', 278 | 'paper': 'https://github.com/microsoft/distribution-shift-latent-representations'}, 279 | {'title': 'NeurIPS DistShift Workshop 2021', 280 | 'paper': 'https://sites.google.com/view/distshift2021'}, 281 | {'title': 'Types of Out-of-Distribution Texts and How to Detect Them', 282 | 'paper': 'https://aclanthology.org/2021.emnlp-main.835.pdf'}, 283 | {'title': 'Looking Beyond Label Noise: Shifted Label Distribution Matters in Distantly Supervised Relation Extraction', 284 | 'paper': 'https://aclanthology.org/D19-1397.pdf'}, 285 | {'title': 'To Annotate or Not? Predicting Performance Drop under Domain Shift', 286 | 'paper': 'https://aclanthology.org/D19-1222.pdf'}, 287 | {'title': '2022.acl-long.223.pdf', 288 | 'paper': 'https://aclanthology.org/2022.acl-long.223.pdf'}, 289 | {'title': '2022.repl4nlp-1.1.pdf', 290 | 'paper': 'https://aclanthology.org/2022.repl4nlp-1.1.pdf'}, 291 | {'title': '2022.findings-acl.68.pdf', 292 | 'paper': 'https://aclanthology.org/2022.findings-acl.68.pdf'}, 293 | {'title': '2022.acl-long.74.pdf', 294 | 'paper': 'https://aclanthology.org/2022.acl-long.74.pdf'}, 295 | {'title': '2022.naacl-main.339.pdf', 296 | 'paper': 'https://aclanthology.org/2022.naacl-main.339.pdf'}, 297 | {'title': '[2103.17171] Spectral decoupling allows training transferable neural networks in medical imaging', 298 | 'paper': 'https://arxiv.org/abs/2103.17171'}, 299 | {'title': '[2102.08660] CheXternal: Generalization of Deep Learning Models for Chest X-ray Interpretation to Photos of Chest X-rays and External Clinical Settings', 300 | 'paper': 'https://arxiv.org/abs/2102.08660'}, 301 | {'title': '[2012.10564] Computer-aided abnormality detection in chest radiographs in a clinical setting via domain-adaptation', 302 | 'paper': 'https://arxiv.org/abs/2012.10564'}, 303 | {'title': '[2011.11750] Federated Semi-Supervised Learning for COVID Region Segmentation in Chest CT using Multi-National Data from China, Italy, Japan', 304 | 'paper': 'https://arxiv.org/abs/2011.11750'}, 305 | {'title': '[2010.06667] Chasing Your Long Tails: Differentially Private Prediction in Health Care Settings', 306 | 'paper': 'https://arxiv.org/abs/2010.06667'}, 307 | {'title': '[2007.02035] Shape-aware Meta-learning for Generalizing Prostate MRI Segmentation to Unseen Domains', 308 | 'paper': 'https://arxiv.org/abs/2007.02035'}, 309 | {'title': '[2006.00327] Probabilistic self-learning framework for Low-dose CT Denoising', 310 | 'paper': 'https://arxiv.org/abs/2006.00327'}, 311 | {'title': 'Metric Learning in Optimal Transport for Domain Adaptation', 312 | 'paper': 'https://www.ijcai.org/proceedings/2020/0299.pdf'}, 313 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=hNMOSUxE8o6'}, 314 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=F9ENmZABB0'}, 315 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=aZgiUNye2Cz'}, 316 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=MJgzr6dQPvl'}, 317 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=Bx41qYMdw83'}, 318 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=L3gKhQ2NZyI'}, 319 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=W0fKtUQgcRR'}, 320 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=bAO-2cGNX_j'}, 321 | {'title': 'pdf', 'paper': 'https://openreview.net/pdf?id=2EhHKKXMbG0'}, 322 | {'title': '[2202.10808] Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks', 323 | 'paper': 'https://arxiv.org/abs/2202.10808'}, 324 | {'title': '[2207.11486] Time Series Prediction under Distribution Shift using Differentiable Forgetting', 325 | 'paper': 'https://arxiv.org/abs/2207.11486'}, 326 | {'title': '[2204.10049] On Distribution Shift in Learning-based Bug Detectors', 327 | 'paper': 'https://arxiv.org/abs/2204.10049'}, 328 | {'title': '[2206.00129] Fairness Transferability Subject to Bounded Distribution Shift', 329 | 'paper': 'https://arxiv.org/abs/2206.00129'}, 330 | {'title': '[2208.06604] Combating Label Distribution Shift for Active Domain Adaptation', 331 | 'paper': 'https://arxiv.org/abs/2208.06604'}, 332 | {'title': '[2209.11459] TeST: Test-time Self-Training under Distribution Shift', 333 | 'paper': 'https://arxiv.org/abs/2209.11459'}, 334 | {'title': '[2202.06523] MetaShift: A Dataset of Datasets for Evaluating Contextual Distribution Shifts and Training Conflicts', 335 | 'paper': 'https://arxiv.org/abs/2202.06523'}, 336 | {'title': '[2207.05796] Estimating Test Performance for AI Medical Devices under Distribution Shift with Conformal Prediction', 337 | 'paper': 'https://arxiv.org/abs/2207.05796'}, 338 | {'title': '[2206.13089] Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift', 339 | 'paper': 'https://arxiv.org/abs/2206.13089'}, 340 | {'title': '[2210.00084] Contrastive Graph Few-Shot Learning', 341 | 'paper': 'https://arxiv.org/abs/2210.00084'}, 342 | {'title': '[2210.01360] Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks', 343 | 'paper': 'https://arxiv.org/abs/2210.01360'}, 344 | {'title': '[2210.01979] GAPX: Generalized Autoregressive Paraphrase-Identification X', 345 | 'paper': 'https://arxiv.org/abs/2210.01979'}, 346 | {'title': '[2210.03103] Env-Aware Anomaly Detection: Ignore Style Changes, Stay True to Content!', 347 | 'paper': 'https://arxiv.org/abs/2210.03103'}, 348 | {'title': '[2210.01930] Benchmarking Learnt Radio Localisation under Distribution Shift', 349 | 'paper': 'https://arxiv.org/abs/2210.01930'}, 350 | {'title': '[2209.01332] Class-Specific Channel Attention for Few-Shot Learning', 351 | 'paper': 'https://arxiv.org/abs/2209.01332'}, 352 | {'title': '[2209.01321] Deep Stable Representation Learning on Electronic Health Records', 353 | 'paper': 'https://arxiv.org/abs/2209.01321'}, 354 | {'title': '[2209.15177] Domain Generalization -- A Causal Perspective', 355 | 'paper': 'https://arxiv.org/abs/2209.15177'}, 356 | {'title': '[2209.03620] Black-Box Audits for Group Distribution Shifts', 357 | 'paper': 'https://arxiv.org/abs/2209.03620'}, 358 | {'title': '[2209.05706] Non-Parametric Temporal Adaptation for Social Media Topic Classification', 359 | 'paper': 'https://arxiv.org/abs/2209.05706'}, 360 | {'title': '[2209.05779] Test-Time Adaptation with Principal Component Analysis', 361 | 'paper': 'https://arxiv.org/abs/2209.05779'}, 362 | {'title': 'Unlearn Dataset Bias in Natural Language Inference by Fitting the Residual', 363 | 'paper': 'https://aclanthology.org/D19-6115.pdf'}, 364 | {'title': '2022.findings-naacl.13.pdf', 365 | 'paper': 'https://aclanthology.org/2022.findings-naacl.13.pdf'}, 366 | {'title': '2022.acl-long.256.pdf', 367 | 'paper': 'https://aclanthology.org/2022.acl-long.256.pdf'}, 368 | {'title': '2022.naacl-srw.6.pdf', 369 | 'paper': 'https://aclanthology.org/2022.naacl-srw.6.pdf'}, 370 | {'title': 'Test-Time Training Can Close the Natural Distribution Shift Performance Gap in Deep Learning Based Compressed Sensing', 371 | 'paper': 'https://proceedings.mlr.press/v162/darestani22a/darestani22a.pdf'}, 372 | {'title': 'zhou21g.pdf', 373 | 'paper': 'http://proceedings.mlr.press/v139/zhou21g/zhou21g.pdf'}, 374 | {'title': 'he22a.pdf', 375 | 'paper': 'https://proceedings.mlr.press/v162/he22a/he22a.pdf'}, 376 | {'title': 'Estimating Generalization under Distribution Shifts via Domain-Invariant Representations', 377 | 'paper': 'http://proceedings.mlr.press/v119/chuang20a/chuang20a.pdf'}, 378 | {'title': 'LTF: A Label Transformation Framework for Correcting Target Shift', 379 | 'paper': 'http://proceedings.mlr.press/v119/guo20d/guo20d.pdf'}, 380 | {'title': '07ac7cd13fd0eb1654ccdbd222b81437-Paper.pdf', 381 | 'paper': 'https://papers.nips.cc/paper/2021/file/07ac7cd13fd0eb1654ccdbd222b81437-Paper.pdf'}, 382 | {'title': '8b9e7ab295e87570551db122a04c6f7c-Paper.pdf', 383 | 'paper': 'https://papers.nips.cc/paper/2020/file/8b9e7ab295e87570551db122a04c6f7c-Paper.pdf'}, 384 | {'title': 'd1f255a373a3cef72e03aa9d980c7eca-Paper.pdf', 385 | 'paper': 'https://papers.nips.cc/paper/2021/file/d1f255a373a3cef72e03aa9d980c7eca-Paper.pdf'}, 386 | {'title': '219e052492f4008818b8adb6366c7ed6-Paper.pdf', 387 | 'paper': 'https://papers.nips.cc/paper/2020/file/219e052492f4008818b8adb6366c7ed6-Paper.pdf'}, 388 | {'title': 'Provably Efficient Q-learning with Function Approximation via Distribution Shift Error Checking Oracle', 389 | 'paper': 'https://proceedings.neurips.cc/paper/2019/file/3d8e03e8b133b16f13a586f0c01b6866-Paper.pdf'}, 390 | {'title': 'f5e536083a438cec5b64a4954abc17f1-Paper.pdf', 391 | 'paper': 'https://papers.nips.cc/paper/2020/file/f5e536083a438cec5b64a4954abc17f1-Paper.pdf'}, 392 | {'title': 'Domain Adaptation by Using Causal Inference to Predict Invariant Conditional Distributions', 393 | 'paper': 'https://proceedings.neurips.cc/paper/2018/file/39e98420b5e98bfbdc8a619bef7b8f61-Paper.pdf'}, 394 | {'title': 'dfbfa7ddcfffeb581f50edcf9a0204bb-Paper.pdf', 395 | 'paper': 'https://papers.nips.cc/paper/2020/file/dfbfa7ddcfffeb581f50edcf9a0204bb-Paper.pdf'}, 396 | {'title': 'https://www.ijcai.org/Proceedings/15/Papers/147.pdf', 397 | 'paper': 'https://www.ijcai.org/Proceedings/15/Papers/147.pdf'}, 398 | {'title': 'https://www.ijcai.org/proceedings/2022/0232.pdf', 399 | 'paper': 'https://www.ijcai.org/proceedings/2022/0232.pdf'}, 400 | {'title': 'https://www.ijcai.org/proceedings/2022/0484.pdf', 401 | 'paper': 'https://www.ijcai.org/proceedings/2022/0484.pdf'}, 402 | {'title': 'https://www.ijcai.org/proceedings/2022/0595.pdf', 403 | 'paper': 'https://www.ijcai.org/proceedings/2022/0595.pdf'}, 404 | {'title': 'https://www.ijcai.org/proceedings/2021/0644.pdf', 405 | 'paper': 'https://www.ijcai.org/proceedings/2021/0644.pdf'}, 406 | {'title': 'https://www.ijcai.org/proceedings/2022/0392.pdf', 407 | 'paper': 'https://www.ijcai.org/proceedings/2022/0392.pdf'}, 408 | {'title': 'https://www.ijcai.org/proceedings/2022/0501.pdf', 409 | 'paper': 'https://www.ijcai.org/proceedings/2022/0501.pdf'}, 410 | {'title': 'https://www.ijcai.org/proceedings/2022/0514.pdf', 411 | 'paper': 'https://www.ijcai.org/proceedings/2022/0514.pdf'}, 412 | {'title': 'https://www.ijcai.org/proceedings/2021/0367.pdf', 413 | 'paper': 'https://www.ijcai.org/proceedings/2021/0367.pdf'}, 414 | {'title': 'https://www.ijcai.org/proceedings/2022/0240.pdf', 415 | 'paper': 'https://www.ijcai.org/proceedings/2022/0240.pdf'}, 416 | {'title': 'https://openreview.net/pdf?id=Dl4LetuLdyK', 417 | 'paper': 'https://openreview.net/pdf?id=Dl4LetuLdyK'}, 418 | {'title': 'https://openreview.net/pdf?id=BUQD1tJ2UwK', 419 | 'paper': 'https://openreview.net/pdf?id=BUQD1tJ2UwK'}, 420 | {'title': 'e2d52448d36918c575fa79d88647ba66-Paper.pdf', 421 | 'paper': 'https://proceedings.neurips.cc/paper/2020/file/e2d52448d36918c575fa79d88647ba66-Paper.pdf'}, 422 | {'title': 'fang22a.pdf', 423 | 'paper': 'https://proceedings.mlr.press/v162/fang22a/fang22a.pdf'}, 424 | {'title': 'kang22a.pdf', 425 | 'paper': 'https://proceedings.mlr.press/v162/kang22a/kang22a.pdf'}, 426 | {'title': 'zhao21b.pdf', 427 | 'paper': 'http://proceedings.mlr.press/v130/zhao21b/zhao21b.pdf'}, 428 | {'title': 'yu22i.pdf', 429 | 'paper': 'https://proceedings.mlr.press/v162/yu22i/yu22i.pdf'}, 430 | {'title': 'Can Autonomous Vehicles Identify, Recover From,and Adapt to Distribution Shifts?', 431 | 'paper': 'http://proceedings.mlr.press/v119/filos20a/filos20a.pdf'}, 432 | {'title': 'd8330f857a17c53d217014ee776bfd50-Paper.pdf', 433 | 'paper': 'https://papers.nips.cc/paper/2020/file/d8330f857a17c53d217014ee776bfd50-Paper.pdf'}, 434 | {'title': '0d441de75945e5acbc865406fc9a2559-Paper.pdf', 435 | 'paper': 'https://papers.nips.cc/paper/2021/file/0d441de75945e5acbc865406fc9a2559-Paper.pdf'}, 436 | {'title': '73fed7fd472e502d8908794430511f4d-Paper.pdf', 437 | 'paper': 'https://papers.nips.cc/paper/2021/file/73fed7fd472e502d8908794430511f4d-Paper.pdf'}, 438 | {'title': '8420d359404024567b5aefda1231af24-Paper.pdf', 439 | 'paper': 'https://papers.nips.cc/paper/2021/file/8420d359404024567b5aefda1231af24-Paper.pdf'}, 440 | {'title': '621461af90cadfdaf0e8d4cc25129f91-Paper.pdf', 441 | 'paper': 'https://proceedings.neurips.cc/paper/2019/file/621461af90cadfdaf0e8d4cc25129f91-Paper.pdf'}, 442 | {'title': '[2209.08253] Mitigating Both Covariate and Conditional Shift for Domain Generalization', 443 | 'paper': 'https://arxiv.org/abs/2209.08253'}, 444 | {'title': '[2209.00652] Towards Optimization and Model Selection for Domain Generalization: A Mixup-guided Solution', 445 | 'paper': 'https://arxiv.org/abs/2209.00652'}, 446 | {'title': '[2209.01501] Meta-Learning with Less Forgetting on Large-Scale Non-Stationary Task Distributions', 447 | 'paper': 'https://arxiv.org/abs/2209.01501'}, 448 | {'title': '[2209.02408] Robustness and invariance properties of image classifiers', 449 | 'paper': 'https://arxiv.org/abs/2209.02408'}, 450 | {'title': '[2209.08745] Importance Tempering: Group Robustness for Overparameterized Models', 451 | 'paper': 'https://arxiv.org/abs/2209.08745'}, 452 | {'title': 'RECORD: Resource Constrained Semi-Supervised Learning under Distribution Shift', 453 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3394486.3403214'}, 454 | {'title': 'Towards Reliable Multimodal Stress Detection under Distribution Shift', 455 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3461615.3486570'}, 456 | {'title': 'Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift', 457 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3485447.3512172'}, 458 | {'title': 'Active Model Adaptation Under Unknown Shift', 459 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3534678.3539262'}, 460 | {'title': 'Balance-Subsampled Stable Prediction Across Unknown Test Data', 461 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3477052'}, 462 | {'title': 'Focused Context Balancing for Robust Offline Policy Evaluation', 463 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3292500.3330852'}, 464 | {'title': '3511598', 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3511598'}, 465 | {'title': 'A Critical Reassessment of the Saerens-Latinne-Decaestecker Algorithm for Posterior Probability Adjustment', 466 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3433164'}, 467 | {'title': 'Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Making', 468 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3479552'}, 469 | {'title': 'Co-training Disentangled Domain Adaptation Network for Leveraging Popularity Bias in Recommenders', 470 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3477495.3531952'}, 471 | {'title': 'CausPref: Causal Preference Learning for Out-of-Distribution Recommendation', 472 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3485447.3511969'}, 473 | {'title': 'Off-Policy Actor-critic for Recommender Systems', 474 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3523227.3546758'}, 475 | {'title': 'HybridRepair: towards annotation-efficient repair for deep learning models', 476 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3533767.3534408'}, 477 | {'title': 'Decoupled Reinforcement Learning to Stabilise Intrinsically-Motivated Exploration', 478 | 'paper': 'https://dl.acm.org/doi/pdf/10.5555/3535850.3535978'}, 479 | {'title': 'Neural Statistics for Click-Through Rate Prediction', 480 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3477495.3531762'}, 481 | {'title': 'Influence Function for Unbiased Recommendation', 482 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3397271.3401321'}, 483 | {'title': 'DCAF-BERT: A Distilled Cachable Adaptable Factorized Model For Improved Ads CTR Prediction', 484 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3487553.3524206'}, 485 | {'title': 'Making Adversarially-Trained Language Models Forget with Model Retraining: A Case Study on Hate Speech Detection', 486 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3487553.3524667'}, 487 | {'title': '3455716.3455805', 488 | 'paper': 'https://dl.acm.org/doi/pdf/10.5555/3455716.3455805'}, 489 | {'title': 'AdaRNN', 490 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3459637.3482315'}, 491 | {'title': 'Transfer String Kernel for Cross-Context DNA-Protein Binding Prediction', 492 | 'paper': 'https://dl.acm.org/doi/pdf/10.1109/TCBB.2016.2609918'}, 493 | {'title': 'Real Negatives Matter: Continuous Training with Real Negatives for Delayed Feedback Modeling', 494 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3447548.3467086'}, 495 | {'title': 'A New Generation of Perspective API: Efficient Multilingual Character-level Transformers', 496 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3534678.3539147'}, 497 | {'title': 'Robust Self-Supervised Structural Graph Neural Network for Social Network Prediction', 498 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3485447.3512182'}, 499 | {'title': 'Stable Prediction across Unknown Environments', 500 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3219819.3220082'}, 501 | {'title': '3460120.3484776', 502 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3460120.3484776'}, 503 | {'title': 'Fairness Violations and Mitigation under Covariate Shift', 504 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3442188.3445865'}, 505 | {'title': 'Quantifying the Performance of Adversarial Training on Language Models with Distribution Shifts', 506 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3494108.3522764'}, 507 | {'title': 'FedRS', 508 | 'paper': 'https://dl.acm.org/doi/pdf/10.1145/3447548.3467254'}, 509 | {'title': '[2208.02896] Interpretable Distribution Shift Detection using Optimal Transport', 510 | 'paper': 'https://arxiv.org/abs/2208.02896'}, 511 | {'title': '[2206.05480] CodeS: A Distribution Shift Benchmark Dataset for Source Code Learning', 512 | 'paper': 'https://arxiv.org/abs/2206.05480'}, 513 | {'title': '[2206.08871] How robust are pre-trained models to distribution shift?', 514 | 'paper': 'https://arxiv.org/abs/2206.08871'}, 515 | {'title': '[2207.08977] Calibrated ensembles can mitigate accuracy tradeoffs under distribution shift', 516 | 'paper': 'https://arxiv.org/abs/2207.08977'}, 517 | {'title': '[2202.02339] Discovering Distribution Shifts using Latent Space Representations', 518 | 'paper': 'https://arxiv.org/abs/2202.02339'}, 519 | {'title': '[2207.04075] Models Out of Line: A Fourier Lens on Distribution Shift Robustness', 520 | 'paper': 'https://arxiv.org/abs/2207.04075'}]}} 521 | --------------------------------------------------------------------------------