@inproceedings{472fd8a3952646a7ba428229aabac597,
title = "Analyzing the convergence of federated learning with biased client participation",
abstract = "Federated Learning (FL) is a promising decentralized machine learning framework that enables a massive number of clients (e.g., smartphones) to collaboratively train a global model over the Internet without sacrificing their privacy. Though FL{\textquoteright}s efficacy in non-convex problems is proven, its convergence amidst biased client participation lacks theoretical study. In this paper, we analyze the convergence of FedAvg on non-convex problems, which is the most renowned FL algorithm. We assume even data distribution but non-IID among clients, and elucidate the convergence rate of FedAvg in situations characterized by biased client participation. Our analysis reveals that biased client participation can significantly reduce the precision of the FL model. We validate this through trace-driven experiments, demonstrating that unbiased client participation results in 11% to 50% higher test accuracy compared to extremely biased client participation.",
keywords = "Federated learning, Non-convex, Biased participation, Convergence analysis",
author = "Lei Tan and Miao Hu and Yipeng Zhou and Di Wu",
year = "2023",
doi = "10.1007/978-3-031-46664-9_29",
language = "English",
isbn = "9783031466632",
series = "Lecture Notes in Computer Science",
publisher = "Springer, Springer Nature",
pages = "423--439",
editor = "Xiaochun Yang and Heru Suhartanto and Guoren Wang and Bin Wang and Jing Jiang and Bing Li and Huaijie Zhu and Ningning Cui",
booktitle = "Advanced Data Mining and Applications",
address = "United States",
note = "19th International Conference on Advanced Data Mining and Applications, ADMA 2023 ; Conference date: 21-08-2023 Through 23-08-2023",
}