Framework for Co-distillation Driven Federated Learning to Address Class Imbalance in Healthcare

TL;DR

This paper introduces a co-distillation framework for federated learning in healthcare that effectively addresses class imbalance and bias across clients, improving robustness and performance.

Contribution

It proposes a novel co-distillation approach that enables knowledge sharing among clients without a central server, enhancing class imbalance handling in federated healthcare models.

Findings

Outperforms existing federated methods in class imbalance scenarios

Demonstrates robustness with lower standard deviation as imbalance increases

Achieves better learning outcomes in healthcare federated settings

Abstract

Federated Learning (FL) is a pioneering approach in distributed machine learning, enabling collaborative model training across multiple clients while retaining data privacy. However, the inherent heterogeneity due to imbalanced resource representations across multiple clients poses significant challenges, often introducing bias towards the majority class. This issue is particularly prevalent in healthcare settings, where hospitals acting as clients share medical images. To address class imbalance and reduce bias, we propose a co-distillation driven framework in a federated healthcare setting. Unlike traditional federated setups with a designated server client, our framework promotes knowledge sharing among clients to collectively improve learning outcomes. Our experiments demonstrate that in a federated healthcare setting, co-distillation outperforms other federated methods in handling class imbalance. Additionally, we demonstrate that our framework has the least standard deviation with increasing imbalance while outperforming other baselines, signifying the robustness of our framework for FL in healthcare.