FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction
This work addresses the problem of limited participation of resource-constrained clients in federated learning, representing an incremental improvement over prior submodel extraction techniques.
The paper tackles the challenge of accommodating clients with varied computational capacities in federated learning by proposing FIARSE, a method that dynamically adjusts submodels based on parameter importance, which outperforms existing methods in experiments on various datasets.
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.