└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Awesome Federated Learning [![Awesome](https://awesome.re/badge.svg)](https://awesome.re) 2 | 3 | A list of resources releated to federated learning and privacy in machine learning. 4 | 5 | ## Related Awesome Lists 6 | 7 | * [tushar-semwal/awesome-federated-computing](https://github.com/tushar-semwal/awesome-federated-computing) 8 | 9 | ## Papers 10 | 11 | ### Introduction & Survey 12 | 13 | * Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies https://ieeexplore.ieee.org/document/9780218 14 | 15 | * The Internet of Federated Things (IoFT) https://ieeexplore.ieee.org/document/9611259 16 | 17 | * Advances and Open Problems in Federated Learning https://arxiv.org/pdf/1912.04977.pdf 18 | 19 | * Federated Machine Learning: Concept and Applications https://arxiv.org/pdf/1902.04885 20 | 21 | * Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection https://arxiv.org/abs/1907.09693 22 | 23 | * Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis https://arxiv.org/abs/1802.09941 24 | 25 | * EdgeAI: A Visionfor Deep Learning in IoT Era https://arxiv.org/abs/1910.10356 26 | 27 | * Machine Learning Systems for Highly-Distributed and Rapidly-Growing Data https://arxiv.org/abs/1910.08663 28 | 29 | * No Peek: A Survey of private distributed deep learning https://arxiv.org/pdf/1812.03288 30 | 31 | * Federated Learning in Mobile Edge Networks: A Comprehensive Survey https://arxiv.org/abs/1909.11875 32 | 33 | ### Privacy and Security 34 | 35 | * Federated Learning with Formal Differential Privacy Guarantees https://ai.googleblog.com/2022/02/federated-learning-with-formal.html 36 | 37 | * Applying Differential Privacy to Large Scale Image Classification https://ai.googleblog.com/2022/02/applying-differential-privacy-to-large.html 38 | 39 | * Towards Causal Federated Learning For Enhanced Robustness And Privacy https://arxiv.org/pdf/2104.06557.pdf ICLR DPML 2021 40 | 41 | * FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning https://arxiv.org/abs/2102.02514 42 | 43 | * OpenFL: An open-source framework for Federated Learning https://arxiv.org/abs/2105.06413 44 | 45 | * A Bayesian Federated Learning Framework with Multivariate Gaussian Product https://arxiv.org/abs/2102.01936 46 | 47 | * Communication-Efficient Learning of Deep Networks from Decentralized Data https://arxiv.org/pdf/1602.05629.pdf 48 | 49 | * Practical Secure Aggregation for Federated Learning on User-Held Data https://arxiv.org/abs/1611.04482 50 | 51 | * Practical Secure Aggregation for Privacy-Preserving Machine Learning https://storage.googleapis.com/pub-tools-public-publication-data/pdf/ae87385258d90b9e48377ed49d83d467b45d5776.pdf 52 | 53 | * A Hybrid Approach to Privacy-Preserving Federated Learning https://arxiv.org/abs/1812.03224 54 | 55 | * Analyzing Federated Learning through an Adversarial Lens https://arxiv.org/pdf/1811.12470 56 | 57 | * How To Backdoor Federated Learning https://arxiv.org/abs/1807.00459 58 | 59 | * Comprehensive Privacy Analysis of Deep Learning: Stand-alone and Federated Learning under Passive and Active White-box Inference Attack https://arxiv.org/abs/1812.00910 60 | 61 | * Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning https://arxiv.org/pdf/1812.00535 62 | 63 | * Exploiting Unintended Feature Leakage in Collaborative Learning https://arxiv.org/abs/1805.04049 64 | 65 | * Analyzing Federated Learning through an Adversarial Lens https://arxiv.org/abs/1811.12470 66 | 67 | * Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning https://arxiv.org/abs/1702.07464 68 | 69 | * Protection Against Reconstruction and Its Applications in Private Federated Learning https://arxiv.org/pdf/1812.00984 70 | 71 | * Boosting Privately: Privacy-Preserving Federated Extreme Boosting for Mobile Crowdsensing https://arxiv.org/abs/1907.10218 72 | 73 | * Differentially Private Data Generative Models https://arxiv.org/pdf/1812.02274 74 | 75 | * Differentially Private Federated Learning: A Client Level Perspective https://arxiv.org/abs/1712.07557 76 | 77 | * Privacy-Preserving Collaborative Deep Learning with Unreliable Participants https://arxiv.org/abs/1812.10113 78 | 79 | * Scalable Private Learning with PATE https://arxiv.org/abs/1802.08908 80 | 81 | * Reducing leakage in distributed deep learning for sensitive health data https://www.media.mit.edu/publications/reducing-leakage-in-distributed-deep-learning-for-sensitive-health-data-accepted-to-iclr-2019-workshop-on-ai-for-social-good-2019/ 82 | 83 | * Deep Leakage from Gradients http://papers.nips.cc/paper/9617-deep-leakage-from-gradients.pdf 84 | 85 | * Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning https://arxiv.org/abs/1805.05838 86 | 87 | 88 | ### System and Application 89 | 90 | * Pisces: Efficient Federated Learning via Guided Asynchronous Training https://dl.acm.org/doi/abs/10.1145/3542929.3563463 91 | 92 | * Record and Reward Federated Learning Contributions with Blockchain https://mblocklab.com/RecordandReward.pdf 93 | 94 | * Flower: A Friendly Federated Learning Framework https://arxiv.org/pdf/2007.14390.pdf 95 | 96 | * Learning Private Neural Language Modeling with Attentive Aggregation https://arxiv.org/pdf/1812.07108 97 | 98 | * Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning https://arxiv.org/abs/2003.09603 99 | 100 | * Decentralized Knowledge Acquisition for Mobile Internet Applications https://link.springer.com/article/10.1007/s11280-019-00775-w 101 | 102 | * A generic framework for privacy preserving deep learning https://arxiv.org/pdf/1811.04017.pdf 103 | 104 | * Federated Learning of N-gram Language Models https://arxiv.org/pdf/1910.03432.pdf 105 | 106 | * Towards Federated Learning at Scale: System Design https://arxiv.org/pdf/1902.01046.pdf 107 | 108 | * Federated Learning for Keyword Spotting https://arxiv.org/abs/1810.05512 109 | 110 | * Federated Learning in Distributed Medical Databases: Meta-Analysis of Large-Scale Subcortical Brain Data https://arxiv.org/abs/1810.08553 111 | 112 | * Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System https://arxiv.org/pdf/1901.09888 113 | 114 | * Confederated Machine Learning on Horizontally and Vertically Separated Medical Data for Large-Scale Health System Intelligence https://arxiv.org/abs/1910.02109 115 | 116 | * Privacy-Preserving Deep Learning Computation for Geo-Distributed Medical Big-Data Platform http://www.cs.ucf.edu/~mohaisen/doc/dsn19b.pdf 117 | 118 | * Institutionally Distributed Deep Learning Networks https://arxiv.org/abs/1709.05929 119 | 120 | * Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation https://arxiv.org/abs/1810.04304 121 | 122 | * Split learning for health: Distributed deep learning without sharing raw patient data https://www.media.mit.edu/publications/split-learning-for-health-distributed-deep-learning-without-sharing-raw-patient-data/ 123 | 124 | * Continuous Delivery for Machine Learning https://martinfowler.com/articles/cd4ml.html#EvolvingIntelligentSystemsWithoutBias 125 | 126 | * Ease.ml/ci & Ease.ml/meter Towards Data Management for Statistical Generialization http://ease.ml/ 127 | 128 | * VisionAir: Using Federated Learning to estimate Air Quality using the Tensorflow API for Java https://blog.tensorflow.org/2020/02/visionair-using-federated-learning-to-estimate-airquality-tensorflow-api-java.html 129 | 130 | * Federated Optimization in Heterogeneous Networks https://arxiv.org/abs/1812.06127 131 | 132 | 133 | 134 | ### Un-org 135 | 136 | * FedProf: Optimizing Federated Learning with Dynamic Data Profiling https://arxiv.org/abs/2102.01733 137 | 138 | * FedBN: Federated Learning on Non-IID Features via Local Batch Normalization https://arxiv.org/abs/2102.07623 139 | 140 | * A Scalable Approach for Partially Local Federated Learning https://ai.googleblog.com/2021/12/a-scalable-approach-for-partially-local.html?m=1 141 | 142 | * Federated Visual Classification with Real-World Data Distribution https://arxiv.org/abs/2003.08082 143 | 144 | * Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification https://arxiv.org/abs/1909.06335 145 | 146 | * LEAF: A Benchmark for Federated Settings https://arxiv.org/abs/1812.01097 147 | 148 | * On the Convergence of FedAvg on Non-IID Data https://arxiv.org/abs/1907.02189 149 | 150 | * Privacy-preserving Federated Brain Tumour Segmentation. https://arxiv.org/pdf/1910.00962.pdf 151 | 152 | * ExpertMatcher: Automating ML Model Selection for Users in Resource Constrained Countries https://www.media.mit.edu/publications/ExpertMatcher/ 153 | 154 | * Detailed comparison of communication efficiency of split learning and federated learning https://www.media.mit.edu/publications/detailed-comparison-of-communication-efficiency-of-split-learning-and-federated-learning-1/ 155 | 156 | * Split Learning: Distributed and collaborative learning https://aiforsocialgood.github.io/iclr2019/accepted/track1/pdfs/31_aisg_iclr2019.pdf 157 | 158 | * Asynchronous Federated Optimization https://arxiv.org/pdf/1903.03934 159 | 160 | * Robust and Communication-Efficient Federated Learning from Non-IID Data https://arxiv.org/pdf/1903.02891 161 | 162 | * One-Shot Federated Learning https://arxiv.org/pdf/1902.11175 163 | 164 | * High Dimensional Restrictive Federated Model Selection with multi-objective Bayesian Optimization over shifted distributions https://arxiv.org/pdf/1902.08999 165 | 166 | * Agnostic Federated Learning https://arxiv.org/pdf/1902.00146%C2%A0 167 | 168 | * Peer-to-peer Federated Learning on Graphs https://arxiv.org/pdf/1901.11173 169 | 170 | * SecureBoost: A Lossless Federated Learning Framework https://arxiv.org/pdf/1901.08755 171 | 172 | * Federated Reinforcement Learning https://arxiv.org/pdf/1901.08277 173 | 174 | * Lifelong Federated Reinforcement Learning: A Learning Architecture for Navigation in Cloud Robotic Systems https://arxiv.org/pdf/1901.06455 175 | 176 | * Federated Learning via Over-the-Air Computation https://arxiv.org/pdf/1812.11750 177 | 178 | * Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version) https://arxiv.org/pdf/1812.11494 179 | 180 | * Multi-objective Evolutionary Federated Learning https://arxiv.org/pdf/1812.07478 181 | 182 | * Efficient Training Management for Mobile Crowd-Machine Learning: A Deep Reinforcement Learning Approach https://arxiv.org/pdf/1812.03633 183 | 184 | * A Hybrid Approach to Privacy-Preserving Federated Learning https://arxiv.org/pdf/1812.03224 185 | 186 | * Applied Federated Learning: Improving Google Keyboard Query Suggestions https://arxiv.org/pdf/1812.02903 187 | 188 | * Differentially Private Data Generative Models https://arxiv.org/pdf/1812.02274 189 | 190 | * Protection Against Reconstruction and Its Applications in Private Federated Learning https://arxiv.org/pdf/1812.00984 191 | 192 | * Split learning for health: Distributed deep learning without sharing raw patient data https://arxiv.org/pdf/1812.00564 193 | 194 | * Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning https://arxiv.org/pdf/1812.00535 195 | 196 | * LoAdaBoost:Loss-Based AdaBoost Federated Machine Learning on medical Data https://arxiv.org/pdf/1811.12629 197 | 198 | * Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Data https://arxiv.org/pdf/1811.11479 199 | 200 | * Biscotti: A Ledger for Private and Secure Peer-to-Peer Machine Learning https://arxiv.org/pdf/1811.09904 201 | 202 | * Dancing in the Dark: Private Multi-Party Machine Learning in an Untrusted Setting https://arxiv.org/pdf/1811.09712 203 | 204 | * Federated Learning Approach for Mobile Packet Classification https://arxiv.org/abs/1907.13113 205 | 206 | * Collaborative Learning on the Edges: A Case Study on Connected Vehicles https://www.usenix.org/conference/hotedge19/presentation/lu 207 | 208 | * Federated Learning for Time Series Forecasting Using Hybrid Model http://www.diva-portal.se/smash/get/diva2:1334629/FULLTEXT01.pdf 209 | 210 | * Federated Learning: Challenges, Methods, and Future Directions https://arxiv.org/pdf/1908.07873.pdf 211 | 212 | * Federated Learning with Matched Averaging https://openreview.net/forum?id=BkluqlSFDS 213 | 214 | 215 | 216 | ## Code 217 | 218 | * OpenFL: An open-source framework for Federated Learning - https://github.com/intel/openfl 219 | 220 | * Flower https://flower.ai/ 221 | 222 | * PySyft https://github.com/OpenMined/PySyft 223 | 224 | * Tensorflow Federated https://www.tensorflow.org/federated 225 | 226 | * CrypTen https://github.com/facebookresearch/CrypTen 227 | 228 | * FATE https://fate.fedai.org/ 229 | 230 | * DVC https://dvc.org/ 231 | 232 | * LEAF https://leaf.cmu.edu/ 233 | 234 | * Federated iNaturalist/Landmarkds https://github.com/google-research/google-research/tree/master/federated_vision_datasets 235 | 236 | * FedML: A Research Library and Benchmark for Federated Machine Learning https://github.com/FedML-AI/FedML 237 | 238 | * XayNet: Open source framework for federated learning in Rust https://xaynet.webflow.io/ 239 | 240 | * EnvisEdge: https://github.com/NimbleEdge/EnvisEdge 241 | 242 | 243 | ## Use-cases 244 | 245 | MIT CSAIL/Harvard Medical/Tsinghua University’s Academy of Arts and Design 246 | 247 | * https://arxiv.org/ftp/arxiv/papers/1903/1903.09296.pdf 248 | * https://venturebeat.com/2019/03/25/federated-learning-technique-predicts-hospital-stay-and-patient-mortality/ 249 | 250 | Microsoft research/University of Chinese Academy of Sciences, Beijing, China 251 | 252 | * https://arxiv.org/pdf/1907.09173.pdf 253 | 254 | Boston University/Massachusetts General Hospital 255 | 256 | * https://www.ncbi.nlm.nih.gov/pubmed/29500022 257 | 258 | Google 259 | 260 | * https://ai.googleblog.com/2017/04/federated-learning-collaborative.html 261 | * https://www.statnews.com/2019/09/10/google-mayo-clinic-partnership-patient-data/ 262 | 263 | Tencent WeBank 264 | 265 | * https://www.digfingroup.com/webank-clustar/ 266 | 267 | Nvidia/King’s College London, American College of Radiology, MGH and BWH Center for Clinical Data Science, and UCLA Health... etc 268 | 269 | * https://venturebeat.com/2019/10/13/nvidia-uses-federated-learning-to-create-medical-imaging-ai/ 270 | * https://blogs.nvidia.com/blog/2019/12/01/clara-federated-learning/ 271 | 272 | 273 | 274 | 275 | 276 | ## Company 277 | 278 | 279 | * integrate.ai https://integrate.ai 280 | * IntegrateFL: A SaaS platform for Federated Learning https://integrate.ai/integratefl/ 281 | 282 | * Adap https://adap.com/en 283 | 284 | * Snips 285 | * https://snips.ai/ 286 | * https://www.theverge.com/2019/11/21/20975607/sonos-buys-snips-ai-voice-assistant-privacy 287 | 288 | * Privacy.ai https://privacy.ai/ 289 | 290 | * OpenMined https://www.openmined.org/ 291 | 292 | * Arkhn https://arkhn.org/en/ 293 | 294 | * Scaleout https://scaleoutsystems.com/ 295 | 296 | * MELLODDY https://www.melloddy.eu/ 297 | 298 | * DataFleets https://www.datafleets.com/ 299 | 300 | * Xayn AG https://www.xayn.com/ 301 | 302 | * NimbleEdge https://www.nimbleedge.ai/ 303 | --------------------------------------------------------------------------------