MH-pFLID: Model Heterogeneous personalized Federated Learning via Injection and Distillation for Medical Data Analysis
This addresses privacy and resource constraints in medical federated learning, offering a novel approach to handle model heterogeneity, though it is incremental in the context of existing federated learning methods.
The paper tackles the problem of system heterogeneity and non-IID data in federated learning for medical applications by proposing MH-pFLID, a framework that uses a lightweight messenger model for efficient information aggregation without requiring public datasets, achieving improved performance as demonstrated in experiments.
Federated learning is widely used in medical applications for training global models without needing local data access. However, varying computational capabilities and network architectures (system heterogeneity), across clients pose significant challenges in effectively aggregating information from non-independently and identically distributed (non-IID) data. Current federated learning methods using knowledge distillation require public datasets, raising privacy and data collection issues. Additionally, these datasets require additional local computing and storage resources, which is a burden for medical institutions with limited hardware conditions. In this paper, we introduce a novel federated learning paradigm, named Model Heterogeneous personalized Federated Learning via Injection and Distillation (MH-pFLID). Our framework leverages a lightweight messenger model that carries concentrated information to collect the information from each client. We also develop a set of receiver and transmitter modules to receive and send information from the messenger model, so that the information could be injected and distilled with efficiency.