└── README.md /README.md: -------------------------------------------------------------------------------- 1 | # Federated Learning 2 | 3 | ## Part 1: Introduction 4 | * [Federated Learning Comic](https://federated.withgoogle.com/) 5 | * [Federated Learning: Collaborative Machine Learning without Centralized Training Data](http://ai.googleblog.com/2017/04/federated-learning-collaborative.html) 6 | * [GDPR, Data Shotrage and AI (AAAI-19)](https://aaai.org/Conferences/AAAI-19/invited-speakers/#yang) 7 | * [Federated Learning: Machine Learning on Decentralized Data (Google I/O'19)](https://www.youtube.com/watch?v=89BGjQYA0uE) 8 | * [Federated Learning White Paper V1.0](https://www.fedai.org/static/flwp-en.pdf) 9 | * [Federated learning: distributed machine learning with data locality and privacy](https://blog.fastforwardlabs.com/2018/11/14/federated-learning.html) 10 | 11 | ## Part 2: Survey 12 | * [Federated Learning: Challenges, Methods, and Future Directions](https://arxiv.org/abs/1908.07873) 13 | * [Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection](https://arxiv.org/abs/1907.09693) 14 | * [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://arxiv.org/abs/1909.11875) 15 | * [Federated Learning for Wireless Communications: Motivation, Opportunities and Challenges](https://arxiv.org/abs/1908.06847) 16 | * [Convergence of Edge Computing and Deep Learning: A Comprehensive Survey](https://arxiv.org/pdf/1907.08349.pdf) 17 | * [Advances and Open Problems in Federated Learning](https://arxiv.org/pdf/1912.04977.pdf) 18 | * [Federated Machine Learning: Concept and Applications](https://arxiv.org/pdf/1902.04885.pdf) 19 | * [Threats to Federated Learning: A Survey](https://arxiv.org/pdf/2003.02133.pdf) 20 | * [Survey of Personalization Techniques for Federated Learning](https://arxiv.org/pdf/2003.08673.pdf) 21 | * [SECure: A Social and Environmental Certificate for AI Systems](https://arxiv.org/pdf/2006.06217.pdf) 22 | * [From Federated Learning to Fog Learning: Towards Large-Scale Distributed Machine Learning in Heterogeneous Wireless Networks](https://arxiv.org/pdf/2006.03594.pdf) 23 | * [Federated Learning for 6G Communications: Challenges, Methods, and Future Directions](https://arxiv.org/pdf/2006.02931.pdf) 24 | * [A Review of Privacy Preserving Federated Learning for Private IoT Analytics](https://arxiv.org/pdf/2004.11794.pdf) 25 | * [Towards Utilizing Unlabeled Data in Federated Learning: A Survey and Prospective](https://arxiv.org/pdf/2002.11545.pdf) 26 | * [Federated Learning for Resource-Constrained IoT Devices: Panoramas and State-of-the-art](https://arxiv.org/pdf/2002.10610.pdf) 27 | * [Privacy-Preserving Blockchain Based Federated Learning with Differential Data Sharing](https://arxiv.org/pdf/1912.04859.pdf) 28 | * [An Introduction to Communication Efficient Edge Machine Learning](https://arxiv.org/pdf/1912.01554.pdf) 29 | * [Federated Learning for Healthcare Informatics](https://arxiv.org/pdf/1911.06270.pdf) 30 | * [Federated Learning for Coalition Operations](https://arxiv.org/pdf/1910.06799.pdf) 31 | * [No Peek: A Survey of private distributed deep learning](https://arxiv.org/pdf/1812.03288.pdf) 32 | * [Communication-Efficient Edge AI: Algorithms and Systems](http://arxiv.org/pdf/2002.09668.pdf) 33 | 34 | ## Part 3: Benchmarks 35 | * [LEAF: A Benchmark for Federated Settings](https://arxiv.org/abs/1812.01097)(https://github.com/TalwalkarLab/leaf) [Recommend] 36 | * [A Performance Evaluation of Federated Learning Algorithms](https://www.researchgate.net/profile/Gregor_Ulm/publication/329106719_A_Performance_Evaluation_of_Federated_Learning_Algorithms/links/5c0fabcfa6fdcc494febf907/A-Performance-Evaluation-of-Federated-Learning-Algorithms.pdf) 37 | * [Edge AIBench: Towards Comprehensive End-to-end Edge Computing Benchmarking](https://arxiv.org/abs/1908.01924) 38 | 39 | ## Part 4: Converge 40 | ### 4.1 Model Aggregation 41 | * [One-Shot Federated Learning](https://arxiv.org/abs/1902.11175) 42 | * [Federated Learning with Unbiased Gradient Aggregation and Controllable Meta Updating](https://arxiv.org/abs/1910.08234) (NIPS 2019 Workshop) 43 | * [Bayesian Nonparametric Federated Learning of Neural Networks](https://arxiv.org/abs/1905.12022) (ICML 2019) 44 | * [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://openreview.net/forum?id=dgtpE6gKjHn) (ICLR 2021) 45 | * [Agnostic Federated Learning](https://arxiv.org/abs/1902.00146) (ICML 2019) 46 | * [Federated Learning with Matched Averaging](https://openreview.net/forum?id=BkluqlSFDS) (ICLR 2020) 47 | * [Astraea: Self-balancing federated learning for improving classification accuracy of mobile deep learning applications](https://arxiv.org/abs/1907.01132) 48 | 49 | ### 4.2 Convergence Research 50 | * [A Linear Speedup Analysis of Distributed Deep Learning with Sparse and Quantized Communication](https://papers.nips.cc/paper/7519-a-linear-speedup-analysis-of-distributed-deep-learning-with-sparse-and-quantized-communication) （NIPS 2018） 51 | * [Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learning](https://openreview.net/forum?id=jDdzh5ul-d) (ICLR 2021) 52 | * [FetchSGD: Communication-Efficient Federated Learning with Sketching](https://arxiv.org/pdf/2007.07682.pdf) 53 | * [FL-NTK: A Neural Tangent Kernel-based Framework for Federated Learning Convergence Analysis](https://arxiv.org/abs/2105.05001) (ICML 2021) 54 | * [Federated Multi-armed Bandits with Personalization](http://proceedings.mlr.press/v130/shi21c.html) (AISTATS 2021) 55 | * [Federated Learning with Compression: Unified Analysis and Sharp Guarantees](http://proceedings.mlr.press/v130/haddadpour21a.html) (AISTATS 2021) 56 | * [Convergence and Accuracy Trade-Offs in Federated Learning and Meta-Learning](http://proceedings.mlr.press/v130/charles21a.html) (AISTATS 2021) 57 | * [Towards Flexible Device Participation in Federated Learning]() (AISTATS 2021) 58 | * [Fed2: Feature-Aligned Federated Learning](https://dl.acm.org/doi/10.1145/3447548.3467309) (KDD 2021) 59 | * [Federated Optimization for Heterogeneous Networks](https://arxiv.org/pdf/1812.06127) 60 | * [On the Convergence of FedAvg on Non-IID Data](https://arxiv.org/abs/1907.02189) [[OpenReview]](https://openreview.net/forum?id=HJxNAnVtDS) 61 | * [Communication Efficient Decentralized Training with Multiple Local Updates](https://arxiv.org/abs/1910.09126) 62 | * [Local SGD Converges Fast and Communicates Little](https://arxiv.org/abs/1805.09767) 63 | * [SlowMo: Improving Communication-Efficient Distributed SGD with Slow Momentum](https://arxiv.org/abs/1910.00643) 64 | * [Parallel Restarted SGD with Faster Convergence and Less Communication: Demystifying Why Model Averaging Works for Deep Learning](https://arxiv.org/abs/1807.06629) (AAAI 2018） 65 | * [On the Linear Speedup Analysis of Communication Efficient Momentum SGD for Distributed Non-Convex Optimization](https://arxiv.org/abs/1905.03817) (ICML 2019） 66 | * [Communication-efficient on-device machine learning: Federated distillation and augmentation under non-iid private data](https://arxiv.org/abs/1811.11479) 67 | * [Convergence of Distributed Stochastic Variance Reduced Methods without Sampling Extra Data](https://arxiv.org/abs/1905.12648) （NIPS 2019 Workshop) 68 | 69 | ### 4.3 Statistical Heterogeneity 70 | * [FedPD: A Federated Learning Framework with Optimal Rates andAdaptivity to Non-IID Data](https://arxiv.org/pdf/2005.11418.pdf) 71 | * [FedBN: Federated Learning on Non-IID Features via Local Batch Normalization](https://openreview.net/forum?id=6YEQUn0QICG) (ICLR 2021) 72 | * [FedMix: Approximation of Mixup under Mean Augmented Federated Learning](https://openreview.net/forum?id=Ogga20D2HO-) (ICLR 2021) 73 | * [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://openreview.net/forum?id=TNkPBBYFkXg) (ICLR 2021) 74 | * [FedRS: Federated Learning with Restricted Softmax for Label Distribution Non-IID Data](https://dl.acm.org/doi/10.1145/3447548.3467254) (KDD 2021) 75 | * [FedMatch: Federated Learning Over Heterogeneous Question Answering Data](https://dl.acm.org/doi/10.1145/3459637.3482345) (CIKM 2021) 76 | * [Decentralized Learning of Generative Adversarial Networks from Non-iid Data](https://arxiv.org/pdf/1905.09684.pdf) 77 | * [Towards Class Imbalance in Federated Learning](https://arxiv.org/pdf/2008.06217.pdf) 78 | * [Communication-Efficient On-Device Machine Learning:Federated Distillation and Augmentationunder Non-IID Private Data](https://arxiv.org/pdf/1811.11479v1.pdf) 79 | * [Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization](https://arxiv.org/pdf/2007.07481.pdf) 80 | * [Federated Adversarial Domain Adaptation](https://arxiv.org/abs/1911.02054) 81 | * [Federated Learning with Only Positive Labels](https://arxiv.org/pdf/2004.10342.pdf) 82 | * [Federated Learning with Non-IID Data](https://arxiv.org/abs/1806.00582) 83 | * [The Non-IID Data Quagmire of Decentralized Machine Learning](https://arxiv.org/abs/1910.00189) 84 | * [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://arxiv.org/pdf/1903.02891) (IEEE transactions on neural networks and learning systems) 85 | * [FedMD: Heterogenous Federated Learning via Model Distillation](https://arxiv.org/abs/1910.03581) (NIPS 2019 Workshop) 86 | * [First Analysis of Local GD on Heterogeneous Data](https://arxiv.org/abs/1909.04715) 87 | * [SCAFFOLD: Stochastic Controlled Averaging for On-Device Federated Learning](https://arxiv.org/abs/1910.06378) 88 | * [Improving Federated Learning Personalization via Model Agnostic Meta Learning](https://arxiv.org/abs/1909.12488) (NIPS 2019 Workshop) 89 | * [Personalized Federated Learning with First Order Model Optimization](https://openreview.net/forum?id=ehJqJQk9cw) (ICLR 2021) 90 | * [LoAdaBoost: Loss-Based AdaBoost Federated Machine Learning on Medical Data](https://arxiv.org/pdf/1811.12629) 91 | * [On Federated Learning of Deep Networks from Non-IID Data: Parameter Divergence and the Effects of Hyperparametric Methods](https://openreview.net/forum?id=SJeOAJStwB) 92 | * [Overcoming Forgetting in Federated Learning on Non-IID Data](https://arxiv.org/abs/1910.07796) （NIPS 2019 Workshop) 93 | * [FedMAX: Activation Entropy Maximization Targeting Effective Non-IID Federated Learning](#workshop) （NIPS 2019 Workshop) 94 | * [Adaptive Federated Optimization.](https://arxiv.org/pdf/2003.00295.pdf)(ICLR 2021 (Under Review)) 95 | * [Stochastic, Distributed and Federated Optimization for Machine Learning. FL PhD Thesis. By Jakub](https://arxiv.org/pdf/1707.01155.pdf) 96 | * [Collaborative Deep Learning in Fixed Topology Networks](https://arxiv.org/pdf/1706.07880.pdf) 97 | * [FedCD: Improving Performance in non-IID Federated Learning.](https://arxiv.org/pdf/2006.09637.pdf) 98 | * [Life Long Learning: FedFMC: Sequential Efficient Federated Learning on Non-iid Data.](https://arxiv.org/pdf/2006.10937.pdf) 99 | * [Robust Federated Learning: The Case of Affine Distribution Shifts.](https://arxiv.org/pdf/2006.08907.pdf) 100 | * [Exploiting Shared Representations for Personalized Federated Learning](https://arxiv.org/abs/2102.07078) (ICML 2021) 101 | * [Personalized Federated Learning using Hypernetworks](https://arxiv.org/abs/2103.04628) (ICML 2021) 102 | * [Ditto: Fair and Robust Federated Learning Through Personalization](https://onikle.com/articles/359482) (ICML 2021) 103 | * [Data-Free Knowledge Distillation for Heterogeneous Federated Learning](https://arxiv.org/abs/2105.10056) (ICML 2021) 104 | * [Bias-Variance Reduced Local SGD for Less Heterogeneous Federated Learning](https://arxiv.org/abs/2102.03198) (ICML 2021) 105 | * [Heterogeneity for the Win: One-Shot Federated Clustering](https://arxiv.org/abs/2103.00697) (ICML 2021) 106 | * [Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning](https://arxiv.org/abs/2105.05883) (ICML 2021) 107 | * [Federated Deep AUC Maximization for Hetergeneous Data with a Constant Communication Complexity](https://arxiv.org/abs/2102.04635) (ICML 2021) 108 | * [Federated Learning of User Verification Models Without Sharing Embeddings](https://arxiv.org/abs/2104.08776) (ICML 2021) 109 | * [One for One, or All for All: Equilibria and Optimality of Collaboration in Federated Learning](https://arxiv.org/abs/2103.03228) (ICML 2021) 110 | * [Ensemble Distillation for Robust Model Fusion in Federated Learning.](https://arxiv.org/pdf/2006.07242.pdf) 111 | * [XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning.](https://arxiv.org/pdf/2006.05148.pdf) 112 | * [An Efficient Framework for Clustered Federated Learning.](https://arxiv.org/pdf/2006.04088.pdf) 113 | * [Continual Local Training for Better Initialization of Federated Models.](https://arxiv.org/pdf/2005.12657.pdf) 114 | * [FedPD: A Federated Learning Framework with Optimal Rates and Adaptivity to Non-IID Data.](https://arxiv.org/pdf/2005.11418.pdf) 115 | * [Global Multiclass Classification from Heterogeneous Local Models.](https://arxiv.org/pdf/2005.10848.pdf) 116 | * [Multi-Center Federated Learning.](https://arxiv.org/pdf/2005.01026.pdf) 117 | * [Federated Semi-Supervised Learning with Inter-Client Consistency & Disjoint Learning](https://openreview.net/forum?id=ce6CFXBh30h) (ICLR 2021) 118 | * [(*) FedMAX: Mitigating Activation Divergence for Accurate and Communication-Efficient Federated Learning. CMU ECE.](https://arxiv.org/pdf/2004.03657.pdf) 119 | * [(*) Adaptive Personalized Federated Learning](https://arxiv.org/pdf/2003.13461.pdf) 120 | * [Semi-Federated Learning](https://arxiv.org/pdf/2003.12795.pdf) 121 | * [Device Heterogeneity in Federated Learning: A Superquantile Approach.](https://arxiv.org/pdf/2002.11223.pdf) 122 | * [Personalized Federated Learning for Intelligent IoT Applications: A Cloud-Edge based Framework](https://arxiv.org/pdf/2002.10671.pdf) 123 | * [Three Approaches for Personalization with Applications to Federated Learning](https://arxiv.org/pdf/2002.10619.pdf) 124 | * [Personalized Federated Learning: A Meta-Learning Approach](https://arxiv.org/pdf/2002.07948.pdf) 125 | * [Towards Federated Learning: Robustness Analytics to Data Heterogeneity](https://arxiv.org/pdf/2002.05038.pdf) 126 | * [Salvaging Federated Learning by Local Adaptation](https://arxiv.org/pdf/2002.04758.pdf) 127 | * [FOCUS: Dealing with Label Quality Disparity in Federated Learning.](https://arxiv.org/pdf/2001.11359.pdf) 128 | * [Overcoming Noisy and Irrelevant Data in Federated Learning.](https://arxiv.org/pdf/2001.08300.pdf)(ICPR 2020) 129 | * [Real-Time Edge Intelligence in the Making: A Collaborative Learning Framework via Federated Meta-Learning.](https://arxiv.org/pdf/2001.03229.pdf) 130 | * [(*) Think Locally, Act Globally: Federated Learning with Local and Global Representations. NeurIPS 2019 Workshop on Federated Learning distinguished student paper award](https://arxiv.org/pdf/2001.01523.pdf) 131 | * [Federated Learning with Personalization Layers](https://arxiv.org/pdf/1912.00818.pdf) 132 | * [Federated Evaluation of On-device Personalization](https://arxiv.org/pdf/1910.10252.pdf) 133 | * [Measure Contribution of Participants in Federated Learning](https://arxiv.org/pdf/1909.08525.pdf) 134 | * [(*) Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification](https://arxiv.org/pdf/1909.06335.pdf) 135 | * [Multi-hop Federated Private Data Augmentation with Sample Compression](https://arxiv.org/pdf/1907.06426.pdf) 136 | * [Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms](https://arxiv.org/pdf/1906.01736.pdf) 137 | * [High Dimensional Restrictive Federated Model Selection with multi-objective Bayesian Optimization over shifted distributions](https://arxiv.org/pdf/1902.08999.pdf) 138 | * [Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters](https://arxiv.org/pdf/1912.13075.pdf) 139 | * [Towards Efficient Scheduling of Federated Mobile Devices under Computational and Statistical Heterogeneity](https://arxiv.org/pdf/2005.12326.pdf) 140 | * [Client Adaptation improves Federated Learning with Simulated Non-IID Clients](https://arxiv.org/pdf/2007.04806.pdf) 141 | 142 | ### 4.4 Adaptive Aggregation 143 | 144 | * [Asynchronous Federated Learning for Geospatial Applications](https://link.springer.com.remotexs.ntu.edu.sg/chapter/10.1007/978-3-030-14880-5_2) (ECML PKDD Workshop 2018） 145 | * [Asynchronous Federated Optimization](https://arxiv.org/abs/1903.03934) 146 | * [Adaptive Federated Learning in Resource Constrained Edge Computing Systems](https://arxiv.org/abs/1804.05271) (IEEE Journal on Selected Areas in Communications, 2019） 147 | * [The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregation](https://arxiv.org/abs/2102.06387) (ICML 2021) 148 | 149 | ## Part 5: Security 150 | ### 5.1 Adversarial Attacks 151 | * [Can You Really Backdoor Federated Learning? ](https://arxiv.org/abs/1911.07963)(NeruIPS 2019) 152 | * [Model Poisoning Attacks in Federated Learning](https://dais-ita.org/sites/default/files/main_secml_model_poison.pdf) (NIPS workshop 2018） 153 | * [An Overview of Federated Deep Learning Privacy Attacks and Defensive Strategies.](https://arxiv.org/pdf/2004.04676.pdf) 154 | * [How To Backdoor Federated Learning.](https://arxiv.org/pdf/1807.00459.pdf)(AISTATS 2020) 155 | * [Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning.](https://arxiv.org/pdf/1702.07464.pdf)(ACM CCS 2017) 156 | * [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://arxiv.org/pdf/1803.01498.pdf) 157 | * [Deep Leakage from Gradients.](https://papers.nips.cc/paper/9617-deep-leakage-from-gradients.pdf)(NIPS 2019) 158 | * [Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning.](https://arxiv.org/pdf/1812.00910.pdf) 159 | * [Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learning.](https://arxiv.org/pdf/1812.00535.pdf)(INFOCOM 2019) 160 | * [Analyzing Federated Learning through an Adversarial Lens.](https://arxiv.org/pdf/1811.12470.pdf)(ICML 2019） 161 | * [Mitigating Sybils in Federated Learning Poisoning.](https://arxiv.org/pdf/1808.04866.pdf)(RAID 2020) 162 | * [RSA: Byzantine-Robust Stochastic Aggregation Methods for Distributed Learning from Heterogeneous Datasets.](https://arxiv.org/abs/1811.03761)(AAAI 2019) 163 | * [A Framework for Evaluating Gradient Leakage Attacks in Federated Learning.](https://arxiv.org/pdf/2004.10397.pdf) 164 | * [Local Model Poisoning Attacks to Byzantine-Robust Federated Learning.](https://arxiv.org/pdf/1911.11815.pdf) 165 | * [Backdoor Attacks on Federated Meta-Learning](https://arxiv.org/pdf/2006.07026.pdf) 166 | * [Towards Realistic Byzantine-Robust Federated Learning.](https://arxiv.org/pdf/2004.04986.pdf) 167 | * [Data Poisoning Attacks on Federated Machine Learning.](https://arxiv.org/pdf/2004.10020.pdf) 168 | * [Exploiting Defenses against GAN-Based Feature Inference Attacks in Federated Learning.](https://arxiv.org/pdf/2004.12571.pdf) 169 | * [Byzantine-Resilient High-Dimensional SGD with Local Iterations on Heterogeneous Data.](https://arxiv.org/pdf/2006.13041.pdf) 170 | * [FedMGDA+: Federated Learning meets Multi-objective Optimization.](https://arxiv.org/pdf/2006.11489.pdf) 171 | * [Free-rider Attacks on Model Aggregation in Federated Learning](http://proceedings.mlr.press/v130/fraboni21a.html) (AISTATS 2021) 172 | * [FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications.](https://arxiv.org/pdf/2006.15632.pdf) 173 | * [Privacy-preserving Weighted Federated Learning within Oracle-Aided MPC Framework.](https://arxiv.org/pdf/2003.07630.pdf) 174 | * [BASGD: Buffered Asynchronous SGD for Byzantine Learning.](https://arxiv.org/pdf/2003.00937.pdf) 175 | * [Stochastic-Sign SGD for Federated Learning with Theoretical Guarantees.](https://arxiv.org/pdf/2002.10940.pdf) 176 | * [Learning to Detect Malicious Clients for Robust Federated Learning.](https://arxiv.org/pdf/2002.00211.pdf) 177 | * [Robust Aggregation for Federated Learning.](https://arxiv.org/pdf/1912.13445.pdf) 178 | * [Towards Deep Federated Defenses Against Malware in Cloud Ecosystems.](https://arxiv.org/pdf/1912.12370.pdf) 179 | * [Attack-Resistant Federated Learning with Residual-based Reweighting.](https://arxiv.org/pdf/1912.11464.pdf) 180 | * [Free-riders in Federated Learning: Attacks and Defenses.](https://arxiv.org/pdf/1911.12560.pdf) 181 | * [Robust Federated Learning with Noisy Communication.](https://arxiv.org/pdf/1911.00251.pdf) 182 | * [Abnormal Client Behavior Detection in Federated Learning.](https://arxiv.org/pdf/1910.09933.pdf) 183 | * [Eavesdrop the Composition Proportion of Training Labels in Federated Learning.](https://arxiv.org/pdf/1910.06044.pdf) 184 | * [Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging.](https://arxiv.org/pdf/1909.05125.pdf) 185 | * [An End-to-End Encrypted Neural Network for Gradient Updates Transmission in Federated Learning.](https://arxiv.org/pdf/1908.08340.pdf) 186 | * [Secure Distributed On-Device Learning Networks With Byzantine Adversaries.](https://arxiv.org/pdf/1906.00887.pdf) 187 | * [Robust Federated Training via Collaborative Machine Teaching using Trusted Instances.](https://arxiv.org/pdf/1905.02941.pdf) 188 | * [Dancing in the Dark: Private Multi-Party Machine Learning in an Untrusted Setting.](https://arxiv.org/pdf/1811.09712.pdf) 189 | * [Inverting Gradients - How easy is it to break privacy in federated learning?](https://arxiv.org/pdf/2003.14053.pdf) 190 | 191 | ### 5.2 Data Privacy and Confidentiality 192 | 193 | * [Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning](https://arxiv.org/abs/1805.05838) （NIPS 2019 Workshop) 194 | * [Quantification of the Leakage in Federated Learning](https://arxiv.org/pdf/1910.05467.pdf) 195 | 196 | ## Part 6: Communication Efficiency 197 | * [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://arxiv.org/abs/1602.05629)](https://github.com/roxanneluo/Federated-Learning) [Google] **[Must Read]** 198 | * [Two-Stream Federated Learning: Reduce the Communication Costs](https://ieeexplore.ieee.org/document/8698609) (2018 IEEE VCIP) 199 | * [Federated Learning Based on Dynamic Regularization](https://openreview.net/forum?id=B7v4QMR6Z9w) (ICLR 2021) 200 | * [Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms](https://openreview.net/forum?id=GFsU8a0sGB) (ICLR 2021) 201 | * [Adaptive Federated Optimization](https://openreview.net/forum?id=LkFG3lB13U5) (ICLR 2021) 202 | * [PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization](https://arxiv.org/abs/1905.13727) （NIPS 2019） 203 | * [Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training](https://arxiv.org/abs/1712.01887) (ICLR 2018) 204 | * [The Error-Feedback Framework: Better Rates for SGD with Delayed Gradients and Compressed Communication](https://arxiv.org/abs/1909.05350) 205 | * [A Communication Efficient Collaborative Learning Framework for Distributed Features](https://arxiv.org/abs/1912.11187) （NIPS 2019 Workshop) 206 | * [Active Federated Learning](https://arxiv.org/abs/1909.12641) （NIPS 2019 Workshop) 207 | * [Communication-Efficient Distributed Optimization in Networks with Gradient Tracking and Variance Reduction](https://arxiv.org/abs/1909.05844) （NIPS 2019 Workshop) 208 | * [Gradient Descent with Compressed Iterates](https://arxiv.org/abs/1909.04716) （NIPS 2019 Workshop) 209 | * [LAG: Lazily Aggregated Gradient for Communication-Efficient Distributed Learning](https://arxiv.org/abs/1805.09965) 210 | * [Exact Support Recovery in Federated Regression with One-shot Communication](https://arxiv.org/pdf/2006.12583.pdf) 211 | * [DEED: A General Quantization Scheme for Communication Efficiency in Bits](https://arxiv.org/pdf/2006.11401.pdf) 212 | * [Personalized Federated Learning with Moreau Envelopes](https://arxiv.org/pdf/2006.08848.pdf) 213 | * [Towards Flexible Device Participation in Federated Learning for Non-IID Data.](https://arxiv.org/pdf/2006.06954.pdf) 214 | * [A Primal-Dual SGD Algorithm for Distributed Nonconvex Optimization](https://arxiv.org/pdf/2006.03474.pdf) 215 | * [FedSplit: An algorithmic framework for fast federated optimization](https://arxiv.org/pdf/2005.05238.pdf) 216 | * [Distributed Stochastic Non-Convex Optimization: Momentum-Based Variance Reduction](https://arxiv.org/pdf/2005.00224.pdf) 217 | * [On the Outsized Importance of Learning Rates in Local Update Methods.](https://arxiv.org/pdf/2007.00878.pdf) 218 | * [Federated Learning with Compression: Unified Analysis and Sharp Guarantees.](https://arxiv.org/pdf/2007.01154.pdf) 219 | * [From Local SGD to Local Fixed-Point Methods for Federated Learning](https://arxiv.org/pdf/2004.01442.pdf) 220 | * [Federated Residual Learning.](https://arxiv.org/pdf/2003.12880.pdf) 221 | * [Acceleration for Compressed Gradient Descent in Distributed and Federated Optimization.](https://arxiv.org/pdf/2002.11364.pdf)[ICML 2020] 222 | * [Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge](https://arxiv.org/abs/1804.08333) (FedCS) 223 | * [Hybrid-FL for Wireless Networks: Cooperative Learning Mechanism Using Non-IID Data](https://arxiv.org/abs/1905.07210) 224 | * [LASG: Lazily Aggregated Stochastic Gradients for Communication-Efficient Distributed Learning](https://arxiv.org/pdf/2002.11360.pdf) 225 | * [Uncertainty Principle for Communication Compression in Distributed and Federated Learning and the Search for an Optimal Compressor](https://arxiv.org/pdf/2002.08958.pdf) 226 | * [Dynamic Federated Learning](https://arxiv.org/pdf/2002.08782.pdf) 227 | * [Distributed Optimization over Block-Cyclic Data](https://arxiv.org/pdf/2002.07454.pdf) 228 | * [Federated Composite Optimization](https://arxiv.org/abs/2011.08474) (ICML 2021) 229 | * [Distributed Non-Convex Optimization with Sublinear Speedup under Intermittent Client Availability](https://arxiv.org/pdf/2002.07399.pdf) 230 | * [Federated Learning of a Mixture of Global and Local Models](https://arxiv.org/pdf/2002.05516.pdf) 231 | * [Faster On-Device Training Using New Federated Momentum Algorithm](https://arxiv.org/pdf/2002.02090.pdf) 232 | * [FedDANE: A Federated Newton-Type Method](https://arxiv.org/pdf/2001.01920.pdf) 233 | * [Distributed Fixed Point Methods with Compressed Iterates](https://arxiv.org/pdf/1912.09925.pdf) 234 | * [Primal-dual methods for large-scale and distributed convex optimization and data analytics](https://arxiv.org/pdf/1912.08546.pdf) 235 | * [Parallel Restarted SPIDER - Communication Efficient Distributed Nonconvex Optimization with Optimal Computation Complexity](https://arxiv.org/pdf/1912.06036.pdf) 236 | * [Representation of Federated Learning via Worst-Case Robust Optimization Theory](https://arxiv.org/pdf/1912.05571.pdf) 237 | * [On the Convergence of Local Descent Methods in Federated Learning](https://arxiv.org/pdf/1910.14425.pdf) 238 | * [SCAFFOLD: Stochastic Controlled Averaging for Federated Learning](https://arxiv.org/pdf/1910.06378.pdf) 239 | * [Accelerating Federated Learning via Momentum Gradient Descent](https://arxiv.org/pdf/1910.03197.pdf) 240 | * [Robust Federated Learning in a Heterogeneous Environment](https://arxiv.org/pdf/1906.06629.pdf) 241 | * [Scalable and Differentially Private Distributed Aggregation in the Shuffled Model](https://arxiv.org/pdf/1906.08320.pdf) 242 | * [Differentially Private Learning with Adaptive Clipping](https://arxiv.org/pdf/1905.03871.pdf) 243 | * [Semi-Cyclic Stochastic Gradient Descent](https://arxiv.org/pdf/1904.10120.pdf) 244 | * [Federated Optimization in Heterogeneous Networks](https://arxiv.org/pdf/1812.06127.pdf) 245 | * [Partitioned Variational Inference: A unified framework encompassing federated and continual learning](https://arxiv.org/pdf/1811.11206.pdf) 246 | * [Learning Rate Adaptation for Federated and Differentially Private Learning](https://arxiv.org/pdf/1809.03832.pdf) 247 | * [Communication-Efficient Robust Federated Learning Over Heterogeneous Datasets](https://arxiv.org/pdf/2006.09992.pdf) 248 | * [Don’t Use Large Mini-Batches, Use Local SGD](https://arxiv.org/pdf/1808.07217.pdf) 249 | * [Overlap Local-SGD: An Algorithmic Approach to Hide Communication Delays in Distributed SGD](https://arxiv.org/pdf/2002.09539.pdf) 250 | * [Local SGD With a Communication Overhead Depending Only on the Number of Workers](https://arxiv.org/pdf/2006.02582.pdf) 251 | * [Federated Accelerated Stochastic Gradient Descent](https://arxiv.org/pdf/2006.08950.pdf) 252 | * [Tighter Theory for Local SGD on Identical and Heterogeneous Data](https://arxiv.org/pdf/1909.04746.pdf) 253 | * [STL-SGD: Speeding Up Local SGD with Stagewise Communication Period](https://arxiv.org/pdf/2006.06377.pdf) 254 | * [Cooperative SGD: A unified Framework for the Design and Analysis of Communication-Efficient SGD Algorithms](https://arxiv.org/pdf/1808.07576.pdf) 255 | * [Understanding Unintended Memorization in Federated Learning](http://arxiv.org/pdf/2006.07490.pdf) 256 | * [eSGD: Communication Efficient Distributed Deep Learning on the Edge](https://www.usenix.org/conference/hotedge18/presentation/tao) (USENIX 2018 Workshop) 257 | * [CMFL: Mitigating Communication Overhead for Federated Learning](http://home.cse.ust.hk/~lwangbm/CMFL.pdf) 258 | 259 | ### 6.1 Compression 260 | * [Expanding the Reach of Federated Learning by Reducing Client Resource Requirements](https://arxiv.org/abs/1812.07210) 261 | * [Federated Learning: Strategies for Improving Communication Efficiency](https://arxiv.org/abs/1610.05492) （NIPS2016 Workshop) [Google] 262 | * [Natural Compression for Distributed Deep Learning](https://arxiv.org/abs/1905.10988) 263 | * [FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantization](https://arxiv.org/abs/1909.13014) 264 | * [ATOMO: Communication-efficient Learning via Atomic Sparsification](https://arxiv.org/abs/1806.04090)(NIPS 2018） 265 | * [vqSGD: Vector Quantized Stochastic Gradient Descent](https://arxiv.org/abs/1911.07971) 266 | * [QSGD: Communication-efficient SGD via gradient quantization and encoding](https://arxiv.org/abs/1610.02132) （NIPS 2017) 267 | * [Federated Optimization: Distributed Machine Learning for On-Device Intelligence](https://arxiv.org/abs/1610.02527) [Google] 268 | * [Distributed Mean Estimation with Limited Communication](https://arxiv.org/abs/1611.00429) (ICML 2017) 269 | * [Randomized Distributed Mean Estimation: Accuracy vs Communication](https://arxiv.org/abs/1611.07555) 270 | * [Error Feedback Fixes SignSGD and other Gradient Compression Schemes](https://arxiv.org/abs/1901.09847) (ICML 2019） 271 | * [ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning](http://proceedings.mlr.press/v70/zhang17e.html) (ICML 2017) 272 | 273 | ## Part 7: Personalized Federated Learning 274 | ### 7.1 Meta Learning 275 | * [Federated Meta-Learning with Fast Convergence and Efficient Communication](https://arxiv.org/abs/1802.07876) 276 | * [Federated Meta-Learning for Recommendation](https://www.semanticscholar.org/paper/Federated-Meta-Learning-for-Recommendation-Chen-Dong/8e21d353ba283bee8fd18285558e5e8df39d46e8#paper-header) 277 | * [Adaptive Gradient-Based Meta-Learning Methods](https://arxiv.org/abs/1906.02717) 278 | 279 | ### 7.2 Multi-task Learning 280 | * [MOCHA: Federated Multi-Task Learning](https://arxiv.org/abs/1705.10467) (NIPS 2017) 281 | * [Variational Federated Multi-Task Learning](https://arxiv.org/abs/1906.06268) 282 | * [Federated Kernelized Multi-Task Learning](https://mlsys.org/Conferences/2019/doc/2018/30.pdf) 283 | * [Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints](https://arxiv.org/abs/1910.01991) （NIPS 2019 Workshop) 284 | * [Local Stochastic Approximation: A Unified View of Federated Learning and Distributed Multi-Task Reinforcement Learning Algorithms](https://arxiv.org/pdf/2006.13460.pdf) 285 | 286 | ### 7.3 Hierarchical FL 287 | * [Client-Edge-Cloud Hierarchical Federated Learning](https://arxiv.org/pdf/1905.06641.pdf) 288 | * [(FL startup: Tongdun, HangZhou, China) Knowledge Federation: A Unified and Hierarchical Privacy-Preserving AI Framework.](https://arxiv.org/pdf/2002.01647.pdf) 289 | * [HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learning](https://arxiv.org/pdf/2002.11343.pdf) 290 | * [Hierarchical Federated Learning Across Heterogeneous Cellular Networks](https://arxiv.org/pdf/1909.02362.pdf) 291 | * [Enhancing Privacy via Hierarchical Federated Learning](https://arxiv.org/pdf/2004.11361.pdf) 292 | * [Federated learning with hierarchical clustering of local updates to improve training on non-IID data.](https://arxiv.org/pdf/2004.11791.pdf) 293 | * [Federated Hierarchical Hybrid Networks for Clickbait Detection](https://arxiv.org/pdf/1906.00638.pdf) 294 | 295 | ### 7.4 Transfer Learning 296 | * [Secure Federated Transfer Learning. IEEE Intelligent Systems 2018.](https://arxiv.org/pdf/1812.03337.pdf) 297 | * [Secure and Efficient Federated Transfer Learning](https://arxiv.org/pdf/1910.13271.pdf) 298 | * [Wireless Federated Distillation for Distributed Edge Learning with Heterogeneous Data](https://arxiv.org/pdf/1907.02745.pdf) 299 | * [Proxy Experience Replay: Federated Distillation for Distributed Reinforcement Learning.](https://arxiv.org/pdf/2005.06105.pdf) 300 | * [Cooperative Learning via Federated Distillation over Fading Channels](https://arxiv.org/pdf/2002.01337.pdf) 301 | * [(*) Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer](https://arxiv.org/pdf/1912.11279.pdf) 302 | * [Federated Reinforcement Distillation with Proxy Experience Memory](https://arxiv.org/pdf/1907.06536.pdf) 303 | * [Federated Continual Learning with Weighted Inter-client Transfer](https://openreview.net/forum?id=xWr8qQCJU3m) (ICML 2021) 304 | 305 | ## Part 8 Decentralization & Incentive Mechanism 306 | 307 | ### 8.1 Decentralized 308 | * [Communication Compression for Decentralized Training](https://arxiv.org/abs/1803.06443) （NIPS 2018） 309 | * [𝙳𝚎𝚎𝚙𝚂𝚚𝚞𝚎𝚎𝚣𝚎: Decentralization Meets Error-Compensated Compression](https://arxiv.org/abs/1907.07346) 310 | * [Central Server Free Federated Learning over Single-sided Trust Social Networks](https://arxiv.org/pdf/1910.04956.pdf) 311 | * [Can Decentralized Algorithms Outperform Centralized Algorithms? A Case Study for Decentralized Parallel Stochastic Gradient Descent](https://arxiv.org/pdf/1705.09056.pdf) 312 | * [Multi-consensus Decentralized Accelerated Gradient Descent](https://arxiv.org/pdf/2005.00797.pdf) 313 | * [Decentralized Bayesian Learning over Graphs.](https://arxiv.org/pdf/1905.10466.pdf) 314 | * [BrainTorrent: A Peer-to-Peer Environment for Decentralized Federated Learning](https://arxiv.org/pdf/1905.06731.pdf) 315 | * [Biscotti: A Ledger for Private and Secure Peer-to-Peer Machine Learning](https://arxiv.org/pdf/1811.09904.pdf) 316 | * [Matcha: Speeding Up Decentralized SGD via Matching Decomposition Sampling](https://arxiv.org/pdf/1905.09435.pdf) 317 | 318 | ### 8.2 Incentive Mechanism 319 | * [Incentive Mechanism for Reliable Federated Learning: A Joint Optimization Approach to Combining Reputation and Contract Theory](https://ieeexplore.ieee.org/document/8832210) 320 | * [Towards Fair Federated Learning](https://dl.acm.org/doi/10.1145/3447548.3470814) (KDD 2021) 321 | * [Federated Adversarial Debiasing for Fair and Transferable Representations](https://dl.acm.org/doi/10.1145/3447548.3467281) (KDD 2021) 322 | * [Motivating Workers in Federated Learning: A Stackelberg Game Perspective](https://arxiv.org/abs/1908.03092) 323 | * [Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach](https://arxiv.org/abs/1905.07479) 324 | * [Fair Resource Allocation in Federated Learning](https://arxiv.org/pdf/1905.10497v1.pdf) 325 | * [FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MEC.](https://arxiv.org/pdf/2002.09699.pdf)(ICDCS 2020) 326 | * [Toward an Automated Auction Framework for Wireless Federated Learning Services Market](https://arxiv.org/pdf/1912.06370.pdf) 327 | * [Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism](https://arxiv.org/pdf/1911.05642.pdf) 328 | * [A Learning-based Incentive Mechanism forFederated Learning](https://www.u-aizu.ac.jp/~pengli/files/fl_incentive_iot.pdf) 329 | * [A Crowdsourcing Framework for On-Device Federated Learning](https://arxiv.org/pdf/1911.01046.pdf) 330 | * [Rewarding High-Quality Data via Influence Functions](https://arxiv.org/abs/1908.11598) 331 | * [Joint Service Pricing and Cooperative Relay Communication for Federated Learning](https://arxiv.org/abs/1811.12082) 332 | * [Measure Contribution of Participants in Federated Learning](https://arxiv.org/abs/1909.08525) 333 | * [DeepChain: Auditable and Privacy-Preserving Deep Learning with Blockchain-based Incentive](https://eprint.iacr.org/2018/679.pdf) 334 | 335 | 336 | ## Part 9: Vertical Federated Learning 337 | 338 | * [A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression](https://arxiv.org/abs/1912.00513) （NIPS 2019 Workshop) 339 | * [SecureBoost: A Lossless Federated Learning Framework](https://arxiv.org/pdf/1901.08755.pdf) 340 | * [Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator](https://arxiv.org/pdf/1911.09824.pdf) 341 | * [AsySQN: Faster Vertical Federated Learning Algorithms with Better Computation Resource Utilization](https://dl.acm.org/doi/10.1145/3447548.3467169) (KDD 2021) 342 | * [Large-scale Secure XGB for Vertical Federated Learning](https://dl.acm.org/doi/10.1145/3459637.3482361) (CIKM 2021) 343 | * [Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption](https://arxiv.org/pdf/1711.10677.pdf) 344 | * [Entity Resolution and Federated Learning get a Federated Resolution.](https://arxiv.org/pdf/1803.04035.pdf) 345 | * [Multi-Participant Multi-Class Vertical Federated Learning](https://arxiv.org/pdf/2001.11154.pdf) 346 | * [A Communication-Efficient Collaborative Learning Framework for Distributed Features](https://arxiv.org/pdf/1912.11187.pdf) 347 | * [Asymmetrical Vertical Federated Learning](https://arxiv.org/pdf/2004.07427.pdf) 348 | * [VAFL: a Method of Vertical Asynchronous Federated Learning](https://arxiv.org/abs/2007.06081) (ICML workshop on FL, 2020) 349 | * [SplitFed: When Federated Learning Meets Split Learning](https://arxiv.org/abs/2004.12088v2) 350 | * [Privacy Enhanced Multimodal Neural Representations for Emotion Recognition](https://arxiv.org/abs/1910.13212) 351 | * [PrivyNet: A Flexible Framework for Privacy-Preserving Deep Neural Network Training](https://arxiv.org/abs/1709.06161) 352 | * [One Pixel Image and RF Signal Based Split Learning for mmWave Received Power Prediction](https://arxiv.org/abs/1911.01682) 353 | * [Stochastic Distributed Optimization for Machine Learning from Decentralized Features](https://arxiv.org/abs/1812.06415) 354 | 355 | ### Part 10: Wireless Communication and Cloud Computing 356 | 357 | * [Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup](https://arxiv.org/pdf/2006.09801.pdf) 358 | * [Wireless Communications for Collaborative Federated Learning in the Internet of Things](https://arxiv.org/pdf/2006.02499.pdf) 359 | * [Democratizing the Edge: A Pervasive Edge Computing Framework](https://arxiv.org/pdf/2007.00641.pdf) 360 | * [UVeQFed: Universal Vector Quantization for Federated Learning](https://arxiv.org/pdf/2006.03262.pdf) 361 | * [Federated Deep Learning Framework For Hybrid Beamforming in mm-Wave Massive MIMO](https://arxiv.org/pdf/2005.09969.pdf) 362 | * [Efficient Federated Learning over Multiple Access Channel with Differential Privacy Constraints](https://arxiv.org/pdf/2005.07776.pdf) 363 | * [A Secure Federated Learning Framework for 5G Networks](https://arxiv.org/pdf/2005.05752.pdf) 364 | * [Federated Learning and Wireless Communications](https://arxiv.org/pdf/2005.05265.pdf) 365 | * [Lightwave Power Transfer for Federated Learning-based Wireless Networks](https://arxiv.org/pdf/2005.03977.pdf) 366 | * [Towards Ubiquitous AI in 6G with Federated Learning](https://arxiv.org/pdf/2004.13563.pdf) 367 | * [Optimizing Over-the-Air Computation in IRS-Aided C-RAN Systems](https://arxiv.org/pdf/2004.09168.pdf) 368 | * [Network-Aware Optimization of Distributed Learning for Fog Computing](https://arxiv.org/pdf/2004.08488.pdf) 369 | * [On the Design of Communication Efficient Federated Learning over Wireless Networks](https://arxiv.org/pdf/2004.07351.pdf) 370 | * [Federated Machine Learning for Intelligent IoT via Reconfigurable Intelligent Surface](https://arxiv.org/pdf/2004.05843.pdf) 371 | * [Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective](https://arxiv.org/pdf/2004.04314.pdf) 372 | * [Resource Management for Blockchain-enabled Federated Learning: A Deep Reinforcement Learning Approach](https://arxiv.org/pdf/2004.04104.pdf) 373 | * [A Blockchain-based Decentralized Federated Learning Framework with Committee Consensus](https://arxiv.org/pdf/2004.00773.pdf) 374 | * [Scheduling for Cellular Federated Edge Learning with Importance and Channel.](https://arxiv.org/pdf/2004.00490.pdf) 375 | * [Differentially Private Federated Learning for Resource-Constrained Internet of Things.](https://arxiv.org/pdf/2003.12705.pdf) 376 | * [Federated Learning for Task and Resource Allocation in Wireless High Altitude Balloon Networks.](https://arxiv.org/pdf/2003.09375.pdf) 377 | * [Gradient Estimation for Federated Learning over Massive MIMO Communication Systems](https://arxiv.org/pdf/2003.08059.pdf) 378 | * [Adaptive Federated Learning With Gradient Compression in Uplink NOMA](https://arxiv.org/pdf/2003.01344.pdf) 379 | * [Performance Analysis and Optimization in Privacy-Preserving Federated Learning](https://arxiv.org/pdf/2003.00229.pdf) 380 | * [Energy-Efficient Federated Edge Learning with Joint Communication and Computation Design](https://arxiv.org/pdf/2003.00199.pdf) 381 | * [Federated Over-the-Air Subspace Learning and Tracking from Incomplete Data](https://arxiv.org/pdf/2002.12873.pdf) 382 | * [Decentralized Federated Learning via SGD over Wireless D2D Networks](https://arxiv.org/pdf/2002.12507.pdf) 383 | * [Federated Learning in the Sky: Joint Power Allocation and Scheduling with UAV Swarms](https://arxiv.org/pdf/2002.08196.pdf) 384 | * [Wireless Federated Learning with Local Differential Privacy](https://arxiv.org/pdf/2002.05151.pdf) 385 | * [Federated Learning under Channel Uncertainty: Joint Client Scheduling and Resource Allocation.](https://arxiv.org/pdf/2002.01337.pdf) 386 | * [Learning from Peers at the Wireless Edge](https://arxiv.org/pdf/2001.11567.pdf) 387 | * [Convergence of Update Aware Device Scheduling for Federated Learning at the Wireless Edge](https://arxiv.org/pdf/2001.10402.pdf) 388 | * [Communication Efficient Federated Learning over Multiple Access Channels](https://arxiv.org/pdf/2001.08737.pdf) 389 | * [Convergence Time Optimization for Federated Learning over Wireless Networks](https://arxiv.org/pdf/2001.07845.pdf) 390 | * [One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysis](https://arxiv.org/pdf/2001.05713.pdf) 391 | * [Federated Learning with Cooperating Devices: A Consensus Approach for Massive IoT Networks.](https://arxiv.org/pdf/1912.13163.pdf)(IEEE Internet of Things Journal. 2020) 392 | * [Asynchronous Federated Learning with Differential Privacy for Edge Intelligence](https://arxiv.org/pdf/1912.07902.pdf) 393 | * [Federated learning with multichannel ALOHA](https://arxiv.org/pdf/1912.06273.pdf) 394 | * [Federated Learning with Autotuned Communication-Efficient Secure Aggregation](https://arxiv.org/pdf/1912.00131.pdf) 395 | * [Bandwidth Slicing to Boost Federated Learning in Edge Computing](https://arxiv.org/pdf/1911.07615.pdf) 396 | * [Energy Efficient Federated Learning Over Wireless Communication Networks](https://arxiv.org/pdf/1911.02417.pdf) 397 | * [Device Scheduling with Fast Convergence for Wireless Federated Learning](https://arxiv.org/pdf/1911.00856.pdf) 398 | * [Energy-Aware Analog Aggregation for Federated Learning with Redundant Data](https://arxiv.org/pdf/1911.00188.pdf) 399 | * [Age-Based Scheduling Policy for Federated Learning in Mobile Edge Networks](https://arxiv.org/pdf/1910.14648.pdf) 400 | * [Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation](https://arxiv.org/pdf/1910.13067.pdf) 401 | * [Federated Learning over Wireless Networks: Optimization Model Design and Analysis](http://networking.khu.ac.kr/layouts/net/publications/data/2019\)Federated%20Learning%20over%20Wireless%20Network.pdf) 402 | * [Resource Allocation in Mobility-Aware Federated Learning Networks: A Deep Reinforcement Learning Approach](https://arxiv.org/pdf/1910.09172.pdf) 403 | * [Reliable Federated Learning for Mobile Networks](https://arxiv.org/pdf/1910.06837.pdf) 404 | * [Cell-Free Massive MIMO for Wireless Federated Learning](https://arxiv.org/pdf/1909.12567.pdf) 405 | * [A Joint Learning and Communications Framework for Federated Learning over Wireless Networks](https://arxiv.org/pdf/1909.07972.pdf) 406 | * [On Safeguarding Privacy and Security in the Framework of Federated Learning](https://arxiv.org/pdf/1909.06512.pdf) 407 | * [Scheduling Policies for Federated Learning in Wireless Networks](https://arxiv.org/pdf/1908.06287.pdf) 408 | * [Federated Learning with Additional Mechanisms on Clients to Reduce Communication Costs](https://arxiv.org/pdf/1908.05891.pdf) 409 | * [Energy-Efficient Radio Resource Allocation for Federated Edge Learning](https://arxiv.org/pdf/1907.06040.pdf) 410 | * [Mobile Edge Computing, Blockchain and Reputation-based Crowdsourcing IoT Federated Learning: A Secure, Decentralized and Privacy-preserving System](https://arxiv.org/pdf/1906.10893.pdf) 411 | * [Active Learning Solution on Distributed Edge Computing](https://arxiv.org/pdf/1906.10718.pdf) 412 | * [Fast Uplink Grant for NOMA: a Federated Learning based Approach](https://arxiv.org/pdf/1905.04519.pdf) 413 | * [Machine Learning at the Wireless Edge: Distributed Stochastic Gradient Descent Over-the-Air](https://arxiv.org/pdf/1901.00844.pdf) 414 | * [Broadband Analog Aggregation for Low-Latency Federated Edge Learning](https://arxiv.org/pdf/1812.11494.pdf) 415 | * [Federated Echo State Learning for Minimizing Breaks in Presence in Wireless Virtual Reality Networks](https://arxiv.org/pdf/1812.01202.pdf) 416 | * [Joint Service Pricing and Cooperative Relay Communication for Federated Learning](https://arxiv.org/pdf/1811.12082.pdf) 417 | * [In-Edge AI: Intelligentizing Mobile Edge Computing, Caching and Communication by Federated Learning](https://arxiv.org/pdf/1809.07857.pdf) 418 | * [Asynchronous Task Allocation for Federated and Parallelized Mobile Edge Learning](https://arxiv.org/pdf/1905.01656.pdf) 419 | * [Ask to upload some data from client to server Efficient Training Management for Mobile Crowd-Machine Learning: A Deep Reinforcement Learning Approach](https://arxiv.org/abs/1812.03633) 420 | * [Low-latency Broadband Analog Aggregation For Federated Edge Learning](https://arxiv.org/abs/1812.11494) 421 | * [Federated Learning over Wireless Fading Channels](https://arxiv.org/pdf/1907.09769.pdf) 422 | * [Federated Learning via Over-the-Air Computation](https://arxiv.org/abs/1812.11750) 423 | 424 | ## Part 11: Federated with Deep learning 425 | 426 | ### 11.1 Neural Architecture Search(NAS) 427 | * [FedNAS: Federated Deep Learning via Neural Architecture Search.](https://arxiv.org/pdf/2004.08546.pdf)(CVPR 2020) 428 | * [Real-time Federated Evolutionary Neural Architecture Search.](https://arxiv.org/pdf/2003.02793.pdf) 429 | * [Federated Neural Architecture Search.](https://arxiv.org/pdf/2002.06352.pdf) 430 | * [Differentially-private Federated Neural Architecture Search.](https://arxiv.org/pdf/2006.10559.pdf) 431 | 432 | ### 11.2 Graph Neural Network(GNN) 433 | * [SGNN: A Graph Neural Network Based Federated Learning Approach by Hiding Structure](https://ieeexplore.ieee.org/document/9005983) (Big Data) 434 | * [GraphFederator: Federated Visual Analysis for Multi-party Graphs.](https://arxiv.org/abs/2008.11989) 435 | * [FedE: Embedding Knowledge Graphs in Federated Setting](https://arxiv.org/abs/2010.12882) 436 | * [ASFGNN: Automated Separated-Federated Graph Neural Network](https://arxiv.org/abs/2011.03248) 437 | * [GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs](https://arxiv.org/abs/2012.04187) 438 | * [Peer-to-peer Federated Learning on Graphs](https://arxiv.org/abs/1901.11173) 439 | * [Towards Federated Graph Learning for Collaborative Financial Crimes Detection](https://arxiv.org/abs/1909.12946) 440 | * [Secure Deep Graph Generation with Link Differential Privacy](https://arxiv.org/abs/2005.00455v3) (IJCAI 2021) 441 | * [Locally Private Graph Neural Networks](https://arxiv.org/pdf/2006.05535.pdf) (CCS 2021) 442 | * [When Differential Privacy Meets Graph Neural Networks](https://arxiv.org/pdf/2006.05535v1.pdf) 443 | * [Releasing Graph Neural Networks with Differential Privacy](https://arxiv.org/abs/2109.08907) 444 | * [Vertically Federated Graph Neural Network for Privacy-Preserving Node Classification](https://arxiv.org/abs/2005.11903) 445 | * [FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation](https://arxiv.org/abs/2102.04925) (ICML 2021) 446 | * [Decentralized Federated Graph Neural Networks](https://federated-learning.org/fl-ijcai-2021/FTL-IJCAI21_paper_20.pdf) (IJCAI 2021) 447 | * [Federated Graph Classification over Non-IID Graphs](https://arxiv.org/abs/2106.13423) (NeurIPS 2021) 448 | * [SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks](https://arxiv.org/abs/2106.02743) (ICML 2021) 449 | * [FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks](https://arxiv.org/abs/2104.07145) (ICLR 2021) 450 | * [Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling](https://dl.acm.org/doi/10.1145/3447548.3467371) (KDD 2021) 451 | 452 | ## Part 12: FL system & Library & Courses 453 | ### 12.1 System 454 | * [Towards Federated Learning at Scale: System Design](https://arxiv.org/abs/1902.01046) **[Must Read]** 455 | * [Scaling Distributed Machine Learning with System and Algorithm Co-design](https://www.cs.cmu.edu/~muli/file/mu-thesis.pdf) 456 | * [Demonstration of Federated Learning in a Resource-Constrained Networked Environment](https://ieeexplore.ieee.org/document/8784064) 457 | * [Applied Federated Learning: Improving Google Keyboard Query Suggestions](https://arxiv.org/abs/1812.02903) 458 | * [Federated Learning and Differential Privacy: Software tools analysis, the Sherpa.ai FL framework and methodological guidelines for preserving data privacy](https://arxiv.org/abs/2007.00914) 459 | * [FedML: A Research Library and Benchmark for Federated Machine Learning](https://arxiv.org/pdf/2007.13518.pdf) 460 | * [FLeet: Online Federated Learning via Staleness Awareness and Performance Prediction.](https://arxiv.org/pdf/2006.07273.pdf) 461 | * [Heterogeneity-Aware Federated Learning](https://arxiv.org/pdf/2006.06983.pdf) 462 | * [Decentralised Learning from Independent Multi-Domain Labels for Person Re-Identification](https://arxiv.org/pdf/2006.04150.pdf) 463 | * [[startup] Industrial Federated Learning -- Requirements and System Design](https://arxiv.org/pdf/2005.06850.pdf) 464 | * [(*) TiFL: A Tier-based Federated Learning System.](https://arxiv.org/pdf/2001.09249.pdf)(HPDC 2020) 465 | * [Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach](https://arxiv.org/pdf/2001.04756.pdf)(ICDCS 2020) 466 | * [Quantifying the Performance of Federated Transfer Learning](https://arxiv.org/pdf/1912.12795.pdf) 467 | * [ELFISH: Resource-Aware Federated Learning on Heterogeneous Edge Devices](https://arxiv.org/pdf/1912.01684.pdf) 468 | * [Privacy is What We Care About: Experimental Investigation of Federated Learning on Edge Devices](https://arxiv.org/pdf/1911.04559.pdf) 469 | * [Substra: a framework for privacy-preserving, traceable and collaborative Machine Learning](https://arxiv.org/pdf/1910.11567.pdf) 470 | * [BAFFLE : Blockchain Based Aggregator Free Federated Learning](https://arxiv.org/pdf/1909.07452.pdf) 471 | * [Functional Federated Learning in Erlang (ffl-erl)](https://arxiv.org/pdf/1808.08143.pdf) 472 | * [HierTrain: Fast Hierarchical Edge AI Learning With Hybrid Parallelism in Mobile-Edge-Cloud Computing](https://arxiv.org/pdf/2003.09876.pdf) 473 | * [Orpheus: Efficient Distributed Machine Learning via System and Algorithm Co-design](https://petuum.com/wp-content/uploads/2019/01/Orpheus.pdf) 474 | * [Scalable Distributed DNN Training using TensorFlow and CUDA-Aware MPI: Characterization, Designs, and Performance Evaluation](https://arxiv.org/abs/1810.11112) 475 | * [Optimized Broadcast for Deep Learning Workloads on Dense-GPU InfiniBand Clusters: MPI or NCCL?](https://arxiv.org/abs/1707.09414) 476 | * [Optimizing Network Performance for Distributed DNN Training on GPU Clusters: ImageNet/AlexNet Training in 1.5 Minutes](https://arxiv.org/abs/1902.06855) 477 | 478 | 479 | ### 12.2 Courses 480 | 481 | * [Applied Cryptography](https://www.udacity.com/course/applied-cryptography--cs387) 482 | * [A Brief Introduction to Differential Privacy](https://medium.com/georgian-impact-blog/a-brief-introduction-to-differential-privacy-eacf8722283b) 483 | * [Deep Learning with Differential Privacy.](http://doi.acm.org/10.1145/2976749.2978318) 484 | * [Building Safe A.I.](http://iamtrask.github.io/2017/03/17/safe-ai/) 485 | * A Tutorial for Encrypted Deep Learning 486 | * Use Homomorphic Encryption (HE) 487 | 488 | * [Private Deep Learning with MPC](https://mortendahl.github.io/2017/04/17/private-deep-learning-with-mpc/) 489 | * A Simple Tutorial from Scratch 490 | * Use Multiparty Compuation (MPC) 491 | 492 | * [Private Image Analysis with MPC](https://mortendahl.github.io/2017/09/19/private-image-analysis-with-mpc/) 493 | * Training CNNs on Sensitive Data 494 | * Use SPDZ as MPC protocol 495 | 496 | ### 13.2 Secret Sharing 497 | * [Simple Introduction to Sharmir's Secret Sharing and Lagrange Interpolation](https://www.youtube.com/watch?v=kkMps3X_tEE) 498 | * [Secret Sharing, Part 1](https://mortendahl.github.io/2017/06/04/secret-sharing-part1/): Shamir's Secret Sharing & Packed Variant 499 | * [Secret Sharing, Part 2](https://mortendahl.github.io/2017/06/24/secret-sharing-part2/): Improve efficiency 500 | * [Secret Sharing, Part 3](https://mortendahl.github.io/2017/08/13/secret-sharing-part3/) 501 | 502 | 503 | ## Part 13: Secure Multi-party Computation(MPC) 504 | ### 13.1 Differential Privacy 505 | * [Learning Differentially Private Recurrent Language Models](https://arxiv.org/abs/1710.06963) 506 | * [Federated Learning with Bayesian Differential Privacy](https://arxiv.org/abs/1911.10071) （NIPS 2019 Workshop) 507 | * [Private Federated Learning with Domain Adaptation](https://arxiv.org/abs/1912.06733) （NIPS 2019 Workshop) 508 | * [cpSGD: Communication-efficient and differentially-private distributed SGD](https://arxiv.org/abs/1805.10559) 509 | * [Practical Secure Aggregation for Federated Learning on User-Held Data.](https://arxiv.org/pdf/1611.04482.pdf)（NIPS 2016 Workshop) 510 | * [Differentially Private Federated Learning: A Client Level Perspective.](https://arxiv.org/pdf/1712.07557.pdf)（NIPS 2017 Workshop) 511 | * [Exploiting Unintended Feature Leakage in Collaborative Learning.](https://arxiv.org/pdf/1805.04049.pdf)(S&P 2019) 512 | * [A Hybrid Approach to Privacy-Preserving Federated Learning.](https://arxiv.org/pdf/1812.03224.pdf) (AISec 2019) 513 | * [A generic framework for privacy preserving deep learning.](https://arxiv.org/pdf/1811.04017.pdf) (PPML 2018) 514 | * [Federated Generative Privacy.](https://arxiv.org/pdf/1910.08385.pdf)（IJCAI 2019 FL Workshop) 515 | * [Enhancing the Privacy of Federated Learning with Sketching.](https://arxiv.org/pdf/1911.01812.pdf) 516 | * [https://aisec.cc/](https://arxiv.org/pdf/1912.05897.pdf) 517 | * [Federated f-Differential Privacy](http://proceedings.mlr.press/v130/zheng21a.html) (AISTATS 2021) 518 | * [Shuffled Model of Differential Privacy in Federated Learning](http://proceedings.mlr.press/v130/girgis21a.html) (AISTATS 2021) 519 | * [Differentially Private Federated Knowledge Graphs Embedding](https://dl.acm.org/doi/10.1145/3459637.3482252) (CIKM 2021) 520 | * [Anonymizing Data for Privacy-Preserving Federated Learning.](https://arxiv.org/pdf/2002.09096.pdf) 521 | * [Practical and Bilateral Privacy-preserving Federated Learning.](https://arxiv.org/pdf/2002.09843.pdf) 522 | * [Decentralized Policy-Based Private Analytics.](https://arxiv.org/pdf/2003.06612.pdf) 523 | * [FedSel: Federated SGD under Local Differential Privacy with Top-k Dimension Selection.](https://arxiv.org/pdf/2003.10637.pdf) (DASFAA 2020) 524 | * [Learn to Forget: User-Level Memorization Elimination in Federated Learning.](https://arxiv.org/pdf/2003.10933.pdf) 525 | * [LDP-Fed: Federated Learning with Local Differential Privacy.](https://arxiv.org/pdf/2006.03637.pdf)（EdgeSys 2020) 526 | * [PrivFL: Practical Privacy-preserving Federated Regressions on High-dimensional Data over Mobile Networks.](https://arxiv.org/pdf/2004.02264.pdf) 527 | * [Local Differential Privacy based Federated Learning for Internet of Things.](https://arxiv.org/pdf/2004.08856.pdf) 528 | * [Differentially Private AirComp Federated Learning with Power Adaptation Harnessing Receiver Noise.](https://arxiv.org/pdf/2004.06337.pdf) 529 | * [Decentralized Differentially Private Segmentation with PATE.](https://arxiv.org/pdf/2004.06567.pdf)（MICCAI 2020 Under Review) 530 | * [Privacy Preserving Distributed Machine Learning with Federated Learning.](https://arxiv.org/pdf/2004.12108.pdf) 531 | * [Exploring Private Federated Learning with Laplacian Smoothing.](https://arxiv.org/pdf/2005.00218.pdf) 532 | * [Information-Theoretic Bounds on the Generalization Error and Privacy Leakage in Federated Learning.](https://arxiv.org/pdf/2005.02503.pdf) 533 | * [Efficient Privacy Preserving Edge Computing Framework for Image Classification.](https://arxiv.org/pdf/2005.04563.pdf) 534 | * [A Distributed Trust Framework for Privacy-Preserving Machine Learning.](https://arxiv.org/pdf/2006.02456.pdf) 535 | * [Secure Byzantine-Robust Machine Learning.](https://arxiv.org/pdf/2006.04747.pdf) 536 | * [ARIANN: Low-Interaction Privacy-Preserving Deep Learning via Function Secret Sharing.](https://arxiv.org/pdf/2006.04593.pdf) 537 | * [Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control.](https://arxiv.org/pdf/2006.05459.pdf) 538 | * [(*) Distributed Differentially Private Averaging with Improved Utility and Robustness to Malicious Parties.](https://arxiv.org/pdf/2006.07218.pdf) 539 | * [GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators.](https://arxiv.org/pdf/2006.08848.pdf) 540 | * [Federated Learning with Differential Privacy:Algorithms and Performance Analysis](https://arxiv.org/pdf/1911.00222.pdf) 541 | 542 | ### 13.2 Secret Sharing 543 | * [Simple Introduction to Sharmir's Secret Sharing and Lagrange Interpolation](https://www.youtube.com/watch?v=kkMps3X_tEE) 544 | * [Secret Sharing, Part 1](https://mortendahl.github.io/2017/06/04/secret-sharing-part1/): Shamir's Secret Sharing & Packed Variant 545 | * [Secret Sharing, Part 2](https://mortendahl.github.io/2017/06/24/secret-sharing-part2/): Improve efficiency 546 | * [Secret Sharing, Part 3](https://mortendahl.github.io/2017/08/13/secret-sharing-part3/) 547 | 548 | 549 | ## Part 14: Applications 550 | 551 | * [Federated Learning Approach for Mobile Packet Classification](https://arxiv.org/abs/1907.13113) 552 | * [Federated Learning for Ranking Browser History Suggestions](https://arxiv.org/abs/1911.11807) (NIPS 2019 Workshop) 553 | 554 | ### 14.1 Healthcare 555 | * [HHHFL: Hierarchical Heterogeneous Horizontal Federated Learning for Electroencephalography](https://arxiv.org/abs/1909.05784) (NIPS 2019 Workshop) 556 | * [Learn Electronic Health Records by Fully Decentralized Federated Learning](https://arxiv.org/abs/1912.01792) (NIPS 2019 Workshop) 557 | * [FLOP: Federated Learning on Medical Datasets using Partial Networks](https://dl.acm.org/doi/10.1145/3447548.3467185) (KDD 2021) 558 | * [Patient Clustering Improves Efficiency of Federated Machine Learning to predict mortality and hospital stay time using distributed Electronic Medical Records](https://arxiv.org/ftp/arxiv/papers/1903/1903.09296.pdf) [[News]](https://venturebeat.com/2019/03/25/federated-learning-technique-predicts-hospital-stay-and-patient-mortality/) 559 | * [Federated learning of predictive models from federated Electronic Health Records.](https://www.ncbi.nlm.nih.gov/pubmed/29500022) 560 | * [FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare](https://arxiv.org/pdf/1907.09173.pdf) 561 | * [Multi-Institutional Deep Learning Modeling Without Sharing Patient Data: A Feasibility Study on Brain Tumor Segmentation](https://arxiv.org/pdf/1810.04304.pdf) 562 | * [NVIDIA Clara Federated Learning to Deliver AI to Hospitals While Protecting Patient Data](https://blogs.nvidia.com/blog/2019/12/01/clara-federated-learning/) 563 | * [What is Federated Learning](https://blogs.nvidia.com/blog/2019/10/13/what-is-federated-learning/) 564 | * [Split learning for health: Distributed deep learning without sharing raw patient data](https://arxiv.org/pdf/1812.00564) 565 | * [Two-stage Federated Phenotyping and Patient Representation Learning](https://www.aclweb.org/anthology/W19-5030.pdf) (ACL 2019) 566 | * [Federated Tensor Factorization for Computational Phenotyping](https://dl.acm.org/doi/10.1145/3097983.3098118) (SIGKDD 2017) 567 | * [FedHealth- A Federated Transfer Learning Framework for Wearable Healthcare](https://arxiv.org/abs/1907.09173) (ICJAI 2019 workshop) 568 | * [Multi-Institutional Deep Learning Modeling Without Sharing Patient Data- A Feasibility Study on Brain Tumor Segmentation](https://arxiv.org/abs/1810.04304) (MICCAI'18 Workshop) 569 | * [Federated Patient Hashing](https://aaai.org/ojs/index.php/AAAI/article/view/6121) (AAAI 2020) 570 | 571 | ### 14.2 Natual Language Processing 572 | 573 | Google 574 | 575 | * [Federated Learning for Mobile Keyboard Prediction](https://arxiv.org/abs/1811.03604) 576 | * [Applied Federated Learning: Improving Google Keyboard Query Suggestions](https://arxiv.org/abs/1812.02903) 577 | * [Federated Learning Of Out-Of-Vocabulary Words](https://arxiv.org/abs/1903.10635) 578 | * [Federated Learning for Emoji Prediction in a Mobile Keyboard](https://arxiv.org/abs/1906.04329) 579 | 580 | Snips 581 | 582 | * [Federated Learning for Wake Keyword Spotting](https://arxiv.org/pdf/1810.05512.pdf) [[Blog]](https://medium.com/snips-ai/federated-learning-for-wake-word-detection-c8b8c5cdd2c5) [[Github]](https://github.com/snipsco/keyword-spotting-research-datasets) 583 | 584 | ### 14.3 Computer Vision 585 | 586 | * [Performance Optimization for Federated Person Re-identification via Benchmark Analysis](https://arxiv.org/abs/2008.11560) (ACMMM 2020) [[Github]](https://github.com/cap-ntu/FedReID) 587 | * [Real-World Image Datasets for Federated Learning](https://arxiv.org/abs/1910.11089) 588 | * [FedVision- An Online Visual Object Detection Platform Powered by Federated Learning](https://arxiv.org/abs/2001.06202) (IAAI20) 589 | * [Federated Learning for Vision-and-Language Grounding Problems](http://web.pkusz.edu.cn/adsp/files/2019/11/AAAI-FenglinL.1027.pdf) (AAAI20) 590 | 591 | ### 14.4 Recommendation 592 | * [Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System](https://arxiv.org/abs/1901.09888) 593 | * [Federated Meta-Learning with Fast Convergence and Efficient Communication](https://arxiv.org/abs/1802.07876) 594 | * [Secure Federated Matrix Factorization](https://arxiv.org/abs/1906.05108) 595 | * [DiFacto: Distributed Factorization Machines](https://www.cs.cmu.edu/~muli/file/difacto.pdf) 596 | 597 | ### 14.5 Industrial 598 | 599 | * [Turbofan POC: Predictive Maintenance of Turbofan Engines using Federated Learning](https://github.com/matthiaslau/Turbofan-Federated-Learning-POC) 600 | * [Turbofan Tycoon Simulation by Cloudera/FastForwardLabs](https://turbofan.fastforwardlabs.com/) 601 | * [Firefox Search Bar](https://florian.github.io/federated-learning/) 602 | 603 | ## Part 15: Organizations and Companies 604 | ### 15.1 国内篇 605 | ##### 微众银行开源 [FATE](https://github.com/FederatedAI/FATE) 框架. 606 | Qiang Yang, Tianjian Chen, Yang Liu, Yongxin Tong. 607 | - [《Federated machine learning: Concept and applications》](https://dl.acm.org/doi/abs/10.1145/3298981) 608 | - [《Secureboost: A lossless federated learning framework》](https://ieeexplore.ieee.org/abstract/document/9440789) 609 | 610 | 611 | ##### 字节跳动开源 [FedLearner](https://github.com/bytedance/fedlearner) 框架. 612 | Jiankai Sun, Weihao Gao, Hongyi Zhang, Junyuan Xie.[《Label Leakage and Protection in Two-party Split learning》](https://arxiv.org/pdf/2102.08504.pdf) 613 | 614 | 615 | ##### 华控清交 PrivPy 多方计算平台 616 | Yi Li, Wei Xu.[《PrivPy: General and Scalable Privacy-Preserving Data Mining》](https://dl.acm.org/doi/pdf/10.1145/3292500.3330920) 617 | 618 | ##### 同盾科技 同盾志邦知识联邦平台 619 | Hongyu Li, Dan Meng, Hong Wang, Xiaolin Li. 620 | - [《Knowledge Federation: A Unified and Hierarchical Privacy-Preserving AI Framework》](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9194566) 621 | - [《FedMONN: Meta Operation Neural Network for Secure Federated Aggregation》](https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9408024) 622 | 623 | ##### 百度 [MesaTEE](https://anquan.baidu.com/product/mesatee) 安全计算平台 624 | Tongxin Li, Yu Ding, Yulong Zhang, Tao Wei.[《gbdt-rs: Fast and Trustworthy Gradient Boosting Decision Tree》](https://www.ieee-security.org/TC/SP2019/posters/hotcrp_sp19posters-final11.pdf) 625 | 626 | ##### 矩阵元 [Rosetta](https://github.com/LatticeX-Foundation/Rosetta) 隐私开源框架 627 | 628 | ##### 百度 [PaddlePaddle](https://github.com/PaddlePaddle/PaddleFL) 开源联邦学习框架 629 | 630 | ##### 蚂蚁区块链科技 [蚂蚁链摩斯安全计算平台](https://antchain.antgroup.com/products/morse) 631 | 632 | ##### 阿里云 [DataTrust](https://dp.alibaba.com/index) 隐私增强计算平台 633 | 634 | ##### 百度百度点石联邦学习平台 635 | 636 | ##### 富数科技 阿凡达安全计算平台 637 | 638 | 639 | 640 | ##### 香港理工大学 641 | 642 | [《FedVision: An Online Visual Object Detection Platform Powered by Federated Learning》](https://ojs.aaai.org//index.php/AAAI/article/view/7021) 643 | 644 | [《BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated Learning》](https://www.usenix.org/system/files/atc20-zhang-chengliang.pdf) 645 | 646 | [《Abnormal Client Behavior Detection in Federated Learning》](https://arxiv.org/pdf/1910.09933.pdf) 647 | 648 | 649 | 650 | ##### 北京航空航天大学 651 | 652 | [《Federated machine learning: Concept and applications》](https://dl.acm.org/doi/abs/10.1145/3298981) 653 | 654 | [《Failure Prediction in Production Line Based on Federated Learning: An Empirical Study》](https://arxiv.org/pdf/2101.11715.pdf) 655 | 656 | 657 | 658 | ### 15.2 国际篇 659 | 660 | Google 提出 Federated Learning. 661 | H. Brendan McMahan. Daniel Ramage. Jakub Konečný. Kallista A. Bonawitz. Hubert Eichner. 662 | 663 | [《Communication-efficient learning of deep networks from decentralized data》](https://arxiv.org/abs/1602.05629) 664 | 665 | [《Federated Learning: Strategies for Improving Communication Efficiency》](https://arxiv.org/abs/1610.05492) 666 | 667 | [《Advances and Open Problems in Federated Learning》](https://arxiv.org/pdf/1912.04977.pdf) 668 | 669 | [《Towards Federated Learning at Scale: System Design》](https://arxiv.org/abs/1902.01046) 670 | 671 | [《Differentially Private Learning with Adaptive Clipping》](https://arxiv.org/pdf/1905.03871.pdf) 672 | 673 | ......（更多联邦学习相关文章请自行搜索 Google Scholar） 674 | 675 | 676 | 677 | #### Cornell University. 678 | 679 | Antonio Marcedone. 680 | 681 | [《Practical Secure Aggregation for Federated Learning on User-Held Data》](https://arxiv.org/pdf/1611.04482.pdf) 682 | 683 | [《Practical Secure Aggregation for Privacy-Preserving Machine Learning》](https://academic.microsoft.com/paper/2949130532/citedby/search?q=Practical%20Secure%20Aggregation%20for%20Privacy%20Preserving%20Machine%20Learning.&qe=RId%253D2949130532&f=&orderBy=0) 684 | 685 | Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, Vitaly Shmatikov. 686 | 687 | [《How To Backdoor Federated Learning》](https://arxiv.org/pdf/1807.00459.pdf) 688 | 689 | [《Differential privacy has disparate impact on model accuracy》](https://proceedings.neurips.cc/paper/2019/hash/fc0de4e0396fff257ea362983c2dda5a-Abstract.html) 690 | 691 | Ziteng Sun. 692 | 693 | [《Can you really backdoor federated learning?》](https://arxiv.org/abs/1911.07963) 694 | --------------------------------------------------------------------------------