AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation

TL;DR

AdaBest introduces an adaptive method for accurately estimating and mitigating client drift in federated learning, leading to faster convergence and higher accuracy with reduced resource usage.

Contribution

It presents a novel adaptive algorithm that improves drift estimation accuracy while reducing storage, communication, and computation costs in federated learning.

Findings

Faster convergence compared to baselines

Higher accuracy across various benchmarks

Reduced resource requirements

Abstract

In Federated Learning (FL), a number of clients or devices collaborate to train a model without sharing their data. Models are optimized locally at each client and further communicated to a central hub for aggregation. While FL is an appealing decentralized training paradigm, heterogeneity among data from different clients can cause the local optimization to drift away from the global objective. In order to estimate and therefore remove this drift, variance reduction techniques have been incorporated into FL optimization recently. However, these approaches inaccurately estimate the clients' drift and ultimately fail to remove it properly. In this work, we propose an adaptive algorithm that accurately estimates drift across clients. In comparison to previous works, our approach necessitates less storage and communication bandwidth, as well as lower compute costs. Additionally, our proposed methodology induces stability by constraining the norm of estimates for client drift, making it more practical for large scale FL. Experimental findings demonstrate that the proposed algorithm converges significantly faster and achieves higher accuracy than the baselines across various FL benchmarks.