Inverse Distance Aggregation for Federated Learning with Non-IID Data

TL;DR

This paper introduces IDA, an adaptive weighting method for federated learning that improves model robustness in medical imaging by effectively handling non-IID and unbalanced data across different sites.

Contribution

The paper proposes a novel inverse distance aggregation method that adaptively weights client contributions based on meta-information, addressing data heterogeneity in federated learning.

Findings

IDA outperforms Federated Averaging in non-IID scenarios

The method improves model robustness to noisy and out-of-distribution data

Extensive analysis confirms effectiveness in medical imaging contexts

Abstract

Federated learning (FL) has been a promising approach in the field of medical imaging in recent years. A critical problem in FL, specifically in medical scenarios is to have a more accurate shared model which is robust to noisy and out-of distribution clients. In this work, we tackle the problem of statistical heterogeneity in data for FL which is highly plausible in medical data where for example the data comes from different sites with different scanner settings. We propose IDA (Inverse Distance Aggregation), a novel adaptive weighting approach for clients based on meta-information which handles unbalanced and non-iid data. We extensively analyze and evaluate our method against the well-known FL approach, Federated Averaging as a baseline.