FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction

TL;DR

FIARSE introduces a dynamic, importance-aware submodel extraction method for federated learning, enabling resource-constrained clients to participate effectively while maintaining high model performance.

Contribution

It provides a theoretically grounded, efficient approach for model heterogeneity in federated learning that requires no extra information beyond model parameters.

Findings

Outperforms existing submodel extraction methods in experiments.

Reduces client overhead by eliminating additional importance information.

Enhances participation of resource-limited clients in federated learning.

Abstract

In federated learning (FL), accommodating clients' varied computational capacities poses a challenge, often limiting the participation of those with constrained resources in global model training. To address this issue, the concept of model heterogeneity through submodel extraction has emerged, offering a tailored solution that aligns the model's complexity with each client's computational capacity. In this work, we propose Federated Importance-Aware Submodel Extraction (FIARSE), a novel approach that dynamically adjusts submodels based on the importance of model parameters, thereby overcoming the limitations of previous static and dynamic submodel extraction methods. Compared to existing works, the proposed method offers a theoretical foundation for the submodel extraction and eliminates the need for additional information beyond the model parameters themselves to determine parameter importance, significantly reducing the overhead on clients. Extensive experiments are conducted on various datasets to showcase the superior performance of the proposed FIARSE.