Adaptive Personlization in Federated Learning for Highly Non-i.i.d. Data

TL;DR

This paper introduces an adaptive hierarchical clustering approach in federated learning to enhance personalization and performance in highly non-i.i.d. medical imaging data, outperforming traditional methods.

Contribution

The work proposes a novel clustering-based federated learning method combined with meta-learning for improved personalization on heterogeneous data.

Findings

Significant accuracy improvements over standard FL methods.

Faster convergence within clusters.

Outperforms centralized training with less data.

Abstract

Federated learning (FL) is a distributed learning method that offers medical institutes the prospect of collaboration in a global model while preserving the privacy of their patients. Although most medical centers conduct similar medical imaging tasks, their differences, such as specializations, number of patients, and devices, lead to distinctive data distributions. Data heterogeneity poses a challenge for FL and the personalization of the local models. In this work, we investigate an adaptive hierarchical clustering method for FL to produce intermediate semi-global models, so clients with similar data distribution have the chance of forming a more specialized model. Our method forms several clusters consisting of clients with the most similar data distributions; then, each cluster continues to train separately. Inside the cluster, we use meta-learning to improve the personalization of the participants' models. We compare the clustering approach with classical FedAvg and centralized training by evaluating our proposed methods on the HAM10k dataset for skin lesion classification with extreme heterogeneous data distribution. Our experiments demonstrate significant performance gain in heterogeneous distribution compared to standard FL methods in classification accuracy. Moreover, we show that the models converge faster if applied in clusters and outperform centralized training while using only a small subset of data.