Automating aggregation strategy selection in federated learning

TL;DR

This paper introduces an automated framework for selecting aggregation strategies in federated learning, improving robustness and reducing manual effort across diverse datasets and conditions.

Contribution

It presents a novel end-to-end system that automates and adapts aggregation strategy selection using language models and genetic search.

Findings

Enhances federated learning robustness under non-IID data.

Reduces manual intervention in strategy selection.

Demonstrates effectiveness across diverse datasets.

Abstract

Federated Learning enables collaborative model training without centralising data, but its effectiveness varies with the selection of the aggregation strategy. This choice is non-trivial, as performance varies widely across datasets, heterogeneity levels, and compute constraints. We present an end-to-end framework that automates, streamlines, and adapts aggregation strategy selection for federated learning. The framework operates in two modes: a single-trial mode, where large language models infer suitable strategies from user-provided or automatically detected data characteristics, and a multi-trial mode, where a lightweight genetic search efficiently explores alternatives under constrained budgets. Extensive experiments across diverse datasets show that our approach enhances robustness and generalisation under non-IID conditions while reducing the need for manual intervention. Overall, this work advances towards accessible and adaptive federated learning by automating one of its most critical design decisions, the choice of an aggregation strategy.