2021 · 84 citations · 25 references
ComputingComputer ScienceDistributed SystemsGame TheoryMachine LearningCollaborative LearningCooperative Game TheoryDistributed AlgorithmsFederated LearningOptimization For Machine LearningClient SelectionCollaborative Training EnvironmentsComputational Game TheoryCooperative ModelsOptimization AlgorithmsShapley Operator
The paradigm of Federated learning (FL) deals with multiple clients participating in collaborative training of a machine learning model under the orchestration of a central server. In this setup, each client’s data is private to itself and is not transferable to other clients or the server. Though FL paradigm has received significant interest recently from the research community, the problem of selecting the relevant clients w.r.t. the central server's learning objective is under-explored. We refer to these problems as Federated Relevant Client Selection (FRCS). Because the server doesn't have explicit control over the nature of data possessed by each client, the problem of selecting relevant clients is significantly complex in FL settings. In this paper, we resolve important and related FRCS problems viz., selecting clients with relevant data, detecting clients that possess data relevant to a particular target label, and rectifying corrupted data samples of individual clients. We follow a principled approach to address the above FRCS problems and develop a new federated learning method using the Shapley value concept from cooperative game theory. Towards this end, we propose a cooperative game involving the gradients shared by the clients. Using this game, we compute Shapley values of clients and then present Shapley value based Federated Averaging (S-FedAvg) algorithm that empowers the server to select relevant clients with high probability. S-FedAvg turns out to be critical in designing specific algorithms to address the FRCS problems. We finally conduct a thorough empirical analysis on image classification and speech recognition tasks to show the superior performance of S-FedAvg than the baselines in the context of supervised federated learning settings.
25
Qiang Yang, Yang Liu, Tianjian Chen et al. · ACM Transactions on Intelligent Systems and Technology · 2019 · 5.9K citations
Deep Learning with Differential Privacy
Martı́n Abadi, Andy Chu, Ian Goodfellow et al. · 2016 · 5.9K citations · Full text
Communication-Efficient Learning of Deep Networks from Decentralized Data
H. Brendan McMahan, Eider Moore, Daniel Ramage et al. · arXiv (Cornell University) · 2016 · 5.2K citations · Full text
Game theory: analysis of conflict
Roger B. Myerson · Choice Reviews Online · 1992 · 3.4K citations
Federated Learning with Non-IID Data
Yue Zhao, Meng Li, Liangzhen Lai et al. · arXiv (Cornell University) · 2018 · 1.9K citations · Full text