FedKPer: Tackling Generalization and Personalization in Medical Federated Learning via Knowledge Personalization

TL;DR

FedKPer is a federated learning method designed for medical applications that balances generalization and personalization by selective model alignment and modified aggregation, improving performance across heterogeneous healthcare data.

Contribution

It introduces knowledge personalization during local training and a new aggregation scheme to better handle heterogeneity in medical federated learning.

Findings

FedKPer improves the generalization-personalization trade-off.

The method mitigates forgetting of patient patterns.

It enhances model reliability across diverse healthcare data.

Abstract

Federated learning (FL) holds great potential for medical applications. However, statistical heterogeneity across healthcare institutions poses a major challenge for FL, as the global model struggles both to generalize across unseen patient populations and to adapt to the unique data distributions of individual hospitals. This heterogeneity also exacerbates forgetting at both the global and local level, resulting in previous learned patient patterns to be misclassified after model updates. While prior work has largely treated generalization and personalization as separate challenges, we show that a better balance between the two can be achieved through selective alignment with the global model and a modified aggregation scheme, which together mitigate the effects of statistical heterogeneity. Specifically, we introduce FedKPer, which introduces knowledge personalization into the training stage of each local device. Afterwards, generalization is considered via the global model aggregation process, where local updates that are reliable and label-diverse are emphasized. We evaluate the performance of FedKPer, devising additional metrics that relate to common consequences of forgetting. Overall, we demonstrate FedKPer improves the generalization-personalization trade-off without sacrificing retention.