The Communication-Aware Clustered Federated Learning Problem

Nir Shlezinger, Stefano Rini, Yonina C. Eldar

研究成果: Conference contribution同行評審

22 引文 斯高帕斯(Scopus)


Federated learning (FL) refers to the adaptation of a central model based on data sets available at multiple remote users. Two of the common challenges encountered in FL are the fact that training sets obtained by different users are commonly heterogeneous, i.e., arise from different sample distributions, and the need to communicate large amounts of data between the users and the central server over the typically expensive up-link channel. In this work we formulate the problem of FL in which different clusters of users observe labeled samples drawn from different distributions, while operating under constraints on the communication overhead. For such settings, we identify that the combination of statistical heterogeneity and communication constraints induces a tradeoff between the ability of the users of each cluster to learn a proper model and the accuracy in aggregating these models into a global inference rule. We propose an algorithm based on multi-source adaptation methods for such communication-aware clustered FL scenarios which allows to balance these performance measures, and demonstrate its ability to achieve improved inference over conventional federated averaging without inducing additional communication overhead.

主出版物標題2020 IEEE International Symposium on Information Theory, ISIT 2020 - Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
出版狀態Published - 6月 2020
事件2020 IEEE International Symposium on Information Theory, ISIT 2020 - Los Angeles, United States
持續時間: 21 7月 202026 7月 2020


名字IEEE International Symposium on Information Theory - Proceedings


Conference2020 IEEE International Symposium on Information Theory, ISIT 2020
國家/地區United States
城市Los Angeles


深入研究「The Communication-Aware Clustered Federated Learning Problem」主題。共同形成了獨特的指紋。