Robust Federated Learning Through Representation Matching and Adaptive Hyper-parameters

TL;DR

This paper introduces a robust federated learning approach combining representation matching and adaptive hyper-parameters, improving performance and stability in heterogeneous data scenarios without extensive hyper-parameter tuning.

Contribution

It presents a novel representation matching method and an online hyper-parameter tuning scheme tailored for federated learning with heterogeneous data.

Findings

Significantly improves federated learning robustness.

Enhances model performance across multiple benchmarks.

Reduces divergence of local models in heterogeneous settings.

Abstract

Federated learning is a distributed, privacy-aware learning scenario which trains a single model on data belonging to several clients. Each client trains a local model on its data and the local models are then aggregated by a central party. Current federated learning methods struggle in cases with heterogeneous client-side data distributions which can quickly lead to divergent local models and a collapse in performance. Careful hyper-parameter tuning is particularly important in these cases but traditional automated hyper-parameter tuning methods would require several training trials which is often impractical in a federated learning setting. We describe a two-pronged solution to the issues of robustness and hyper-parameter tuning in federated learning settings. We propose a novel representation matching scheme that reduces the divergence of local models by ensuring the feature representations in the global (aggregate) model can be derived from the locally learned representations. We also propose an online hyper-parameter tuning scheme which uses an online version of the REINFORCE algorithm to find a hyper-parameter distribution that maximizes the expected improvements in training loss. We show on several benchmarks that our two-part scheme of local representation matching and global adaptive hyper-parameters significantly improves performance and training robustness.