Towards Personalized Federated Learning via Heterogeneous Model Reassembly
It addresses the problem of personalized federated learning for clients with heterogeneous models, but it appears incremental as it builds on existing federated learning methods.
The paper tackles model heterogeneity in federated learning by proposing pFedHR, a framework that uses heterogeneous model reassembly for personalization, and it outperforms baselines on three datasets under IID and Non-IID settings.
This paper focuses on addressing the practical yet challenging problem of model heterogeneity in federated learning, where clients possess models with different network structures. To track this problem, we propose a novel framework called pFedHR, which leverages heterogeneous model reassembly to achieve personalized federated learning. In particular, we approach the problem of heterogeneous model personalization as a model-matching optimization task on the server side. Moreover, pFedHR automatically and dynamically generates informative and diverse personalized candidates with minimal human intervention. Furthermore, our proposed heterogeneous model reassembly technique mitigates the adverse impact introduced by using public data with different distributions from the client data to a certain extent. Experimental results demonstrate that pFedHR outperforms baselines on three datasets under both IID and Non-IID settings. Additionally, pFedHR effectively reduces the adverse impact of using different public data and dynamically generates diverse personalized models in an automated manner.