Final papers of FL-ICML’21
- A New Analysis Framework for Federated Learning on Time-Evolving Heterogeneous Data
Yongxin Guo, Tao Lin and Xiaoying Tang
- A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning
Xinyi Xu and Lingjuan Lyu
- Accelerating Federated Learning with Split Learning on Locally Generated Losses
Dong-Jun Han, Hasnain Irshad Bhatti, Jungmoon Lee and Jaekyun Moon
- Achieving Optimal Sample and Communication Complexities for Non-IID Federated Learning
Prashant Khanduri, Pranay Sharma, Haibo Yang, Mingyi Hong, Jia Liu, Ketan Rajawat and Pramod K Varshney
- Bi-directional Adaptive Communication for Heterogenous Distributed Learning
Dmitrii Avdiukhin, Nikita Ivkin, Sebastian U Stich and Vladimir Braverman
- BiG-Fed: Bilevel Optimization Enhanced Graph-Aided Federated Learning
Pengwei Xing, Songtao Lu, Lingfei Wu and Han Yu
- BYGARS: Byzantine SGD with Arbitrary Number of Attackers Using Reputation Scores
Jayanth Regatti, Hao Chen and Abhishek Gupta
- Byzantine Fault-Tolerance of Local Gradient-Descent in Federated Model under 2f-Redundancy
Nirupam Gupta, Thinh Doan and Nitin Vaidya
- Communication and Energy Efficient Slimmable Federated Learning via Superposition Coding and Successive Decoding (full text is temporarily hidden per authors’ request)
Hankyul Baek, Won Joon Yun, Jihong Park, Soyi Jung, Joongheon Kim, Mingyue Ji and Mehdi Bennis
- Decentralized federated learning of deep neural networks on non-iid data
Edvin Listo Zec, Noa Onoszko, Gustav Karlsson and Olof Mogren
- Defending against Reconstruction Attack in Vertical Federated Learning
Jiankai Sun, Yuanshun Yao, Weihao Gao, Junyuan Xie and Chong Wang
- Diverse Client Selection for Federated Learning: Submodularity and Convergence Analysis
Ravikumar Balakrishnan, Tian Li, Tianyi Zhou, Nageen Himayat, Virginia Smith and Jeff Bilmes
- EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback
Peter Richtarik, Igor Sokolov and Ilyas Fatkhullin
- Fed-EINI: An Efficient and Interpretable Inference Framework for Decision Tree Ensembles in Federated Learning
Xiaolin Chen, Shuai Zhou, Kai Yang, Hao Fan, Zejin Feng, Zhong Chen, Yongji Wang and Hu Wang
- Federated Graph Classification over Non-IID Graphs
Han Xie, Jing Ma, Li Xiong and Carl Yang
- Federated Learning with Buffered Asynchronous Aggregation
John Nguyen, Kshitiz Malik, Hongyuan Zhan, Ashkan Yousefpour, Michael Rabbat, Mani Malek and Dzmitry Huba
- Federated Learning with Metric Loss
Hyunsin Park, Hossein Hosseini and Sungrack Yun
- Federated Multi-Task Learning under a Mixture of Distributions
Othmane Marfoq, Giovanni Neglia, Aurélien Bellet, Laetitia Kameni and Richard Vidal
- Federated Random Reshuffling with Compression and Variance Reduction
Grigory Malinovsky and Peter Richtárik
- FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
Chuhan Wu, Fangzhao Wu, Yang Cao, Lingjuan Lyu, Yongfeng Huang and Xing Xie
- FedMix: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning
Elnur Gasanov, Ahmed Khaled, Samuel Horvath and Peter Richtarik
- FedNL: Making Newton-Type Methods Applicable to Federated Learning
Mher Safaryan, Rustem Islamov, Xun Qian and Peter Richtarik
- FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
Samuel Horvath, Stefanos Laskaridis, Mario Almeida, Ilias Leontiadis, Stylianos Venieris and Nicholas Lane
- FlyNN: Fruit-fly Inspired Federated Nearest Neighbor Classification
Parikshit Ram and Kaushik Sinha
- Gradient Inversion with Generative Image Prior
Jinwoo Jeon, Jaechang Kim, Kangwook Lee, Sewoong Oh and Jungseul Ok
- GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalization
Yen-Hsiu Chou, Shenda Hong, Chenxi Sun, Derun Cai, Moxian Song and Hongyan Li
- Handling Both Stragglers and Adversaries for Robust Federated Learning
Jungwuk Park, Dong-Jun Han, Minseok Choi and Jaekyun Moon
- Implicit Gradient Alignment in Distributed and Federated Learning
Yatin Dandi, Luis Barba and Martin Jaggi
- Local Adaptivity in Federated Learning: Convergence and Consistency
Jianyu Wang, Zheng Xu, Zachary Garrett, Zachary Charles, Luyang Liu and Gauri Joshi
- Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization over Time-Varying Networks
Dmitry Kovalev, Elnur Gasanov, Peter Richtarik and Alexander Gasnikov
- Multistage stepsize schedule in Federated Learning: Bridging Theory and Practice
Charlie Hou, Kiran Thekumparampil, Giulia Fanti and Sewoong Oh
- MURANA: A Generic Framework for Stochastic Variance-Reduced Optimization
Laurent Condat and Peter Richtárik
- New Metrics to Evaluate the Performance and Fairness of Personalized Federated Learning
Siddharth Divi, Yi-Shan Lin, Habiba Farrukh and Z Berkay Celik
- OmniLytics: A Blockchain-based Secure Data Market for Decentralized Machine Learning
Jiacheng Liang, Wensi Jiang and Songze Li
- On Large-Cohort Training for Federated Learning
Zachary Charles, Zachary Garrett, Zhouyuan Huo, Sergei Shmulyian and Virginia Smith
- Optimal Model Averaging: Towards Personalized Collaborative Learning
Felix Grimberg, Mary-Anne Hartley, Sai Praneeth Karimireddy and Martin Jaggi
- Robust and Differentially Private Mean Estimation
Xiyang Liu, Weihao Kong, Sham Kakade and Sewoong Oh
- Smoothness-Aware Quantization Techniques
Bokun Wang, Mher Safaryan and Peter Richtarik
- SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks
Chaoyang He, Emir Ceyani, Keshav Balasubramanian, Murali Annavaram and Salman Avestimehr
- Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity
Amirhossein Reisizadeh, Isidoros Tziotis, Hamed Hassani, Aryan Mokhtari and Ramtin Pedarsani
- Subgraph Federated Learning with Missing Neighbor Generation
Ke Zhang, Carl Yang, Xiaoxiao Li, Lichao Sun and Siu Ming Yiu
- Towards Federated Learning With Byzantine-Robust Client Weighting
Amit Portnoy, Yoav Tirosh and Danny Hendler
- Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
Xinwei Zhang, Xiangyi Chen, Mingyi Hong, Zhiwei Steven Wu and Jinfeng Yi