Effective Heterogeneous Federated Learning via Efficient Hypernetwork-based Weight Generation

TL;DR

HypeMeFed is a federated learning framework that uses hypernetworks and multi-exit architectures to effectively support heterogeneous client devices, improving accuracy and efficiency.

Contribution

It introduces a novel hypernetwork-based weight generation method combined with multi-exit networks to handle client heterogeneity in federated learning.

Findings

Accuracy improved by 5.12% over FedAvg

Hypernetwork memory reduced by 98.22%

Operations accelerated by 1.86x

Abstract

While federated learning leverages distributed client resources, it faces challenges due to heterogeneous client capabilities. This necessitates allocating models suited to clients' resources and careful parameter aggregation to accommodate this heterogeneity. We propose HypeMeFed, a novel federated learning framework for supporting client heterogeneity by combining a multi-exit network architecture with hypernetwork-based model weight generation. This approach aligns the feature spaces of heterogeneous model layers and resolves per-layer information disparity during weight aggregation. To practically realize HypeMeFed, we also propose a low-rank factorization approach to minimize computation and memory overhead associated with hypernetworks. Our evaluations on a real-world heterogeneous device testbed indicate that \system enhances accuracy by 5.12% over FedAvg, reduces the hypernetwork memory requirements by 98.22%, and accelerates its operations by 1.86x compared to a naive hypernetwork approach. These results demonstrate HypeMeFed's effectiveness in leveraging and engaging heterogeneous clients for federated learning.