Federated Learning Under Restricted User Availability

Autor:	Theodoropoulos, Periklis, Nikolakakis, Konstantinos E., Kalogerias, Dionysis
Rok vydání:	2023
Předmět:	Computer Science - Machine Learning Computer Science - Distributed Parallel and Cluster Computing Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Federated Learning (FL) is a decentralized machine learning framework that enables collaborative model training while respecting data privacy. In various applications, non-uniform availability or participation of users is unavoidable due to an adverse or stochastic environment, the latter often being uncontrollable during learning. Here, we posit a generic user selection mechanism implementing a possibly randomized, stationary selection policy, suggestively termed as a Random Access Model (RAM). We propose a new formulation of the FL problem which effectively captures and mitigates limited participation of data originating from infrequent, or restricted users, at the presence of a RAM. By employing the Conditional Value-at-Risk (CVaR) over the (unknown) RAM distribution, we extend the expected loss FL objective to a risk-aware objective, enabling the design of an efficient training algorithm that is completely oblivious to the RAM, and with essentially identical complexity as FedAvg. Our experiments on synthetic and benchmark datasets show that the proposed approach achieves significantly improved performance as compared with standard FL, under a variety of setups. Comment: 5 pages, 4 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2309.14176 Zobrazit plný text záznamu View this record from Arxiv