Robust Aggregation for Federated Learning

TL;DR

This paper introduces a robust aggregation method for federated learning that effectively handles corrupted updates from devices, ensuring convergence and improved robustness in diverse settings.

Contribution

It proposes a geometric median-based robust aggregation oracle that is privacy-preserving, converges for least squares models, and outperforms classical methods under high corruption levels.

Findings

Outperforms classical aggregation in high corruption scenarios

Maintains competitiveness in low corruption settings

Includes variants with faster computation and on-device personalization

Abstract

Federated learning is the centralized training of statistical models from decentralized data on mobile devices while preserving the privacy of each device. We present a robust aggregation approach to make federated learning robust to settings when a fraction of the devices may be sending corrupted updates to the server. The approach relies on a robust aggregation oracle based on the geometric median, which returns a robust aggregate using a constant number of iterations of a regular non-robust averaging oracle. The robust aggregation oracle is privacy-preserving, similar to the non-robust secure average oracle it builds upon. We establish its convergence for least squares estimation of additive models. We provide experimental results with linear models and deep networks for three tasks in computer vision and natural language processing. The robust aggregation approach is agnostic to the level of corruption; it outperforms the classical aggregation approach in terms of robustness when the level of corruption is high, while being competitive in the regime of low corruption. Two variants, a faster one with one-step robust aggregation and another one with on-device personalization, round off the paper.