Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies

TL;DR

This paper analyzes how biased client selection strategies in federated learning influence convergence speed, proposing a new Power-of-Choice method that accelerates training and improves accuracy.

Contribution

It provides the first convergence analysis for biased client selection in federated learning and introduces Power-of-Choice, a flexible framework balancing speed and bias.

Findings

Power-of-Choice converges up to 3 times faster.

It achieves 10% higher test accuracy than random selection.

Biasing towards high-loss clients accelerates convergence.

Abstract

Federated learning is a distributed optimization paradigm that enables a large number of resource-limited client nodes to cooperatively train a model without data sharing. Several works have analyzed the convergence of federated learning by accounting of data heterogeneity, communication and computation limitations, and partial client participation. However, they assume unbiased client participation, where clients are selected at random or in proportion of their data sizes. In this paper, we present the first convergence analysis of federated optimization for biased client selection strategies, and quantify how the selection bias affects convergence speed. We reveal that biasing client selection towards clients with higher local loss achieves faster error convergence. Using this insight, we propose Power-of-Choice, a communication- and computation-efficient client selection framework that can flexibly span the trade-off between convergence speed and solution bias. Our experiments demonstrate that Power-of-Choice strategies converge up to 3 $\times$ faster and give $10$% higher test accuracy than the baseline random selection.