FedCostWAvg: A new averaging for better Federated Learning

TL;DR

This paper introduces FedCostWAvg, a novel aggregation method for federated learning that improves model performance by optimizing how models trained on different datasets are averaged, validated through a challenge win.

Contribution

It presents a new weighted averaging strategy for federated learning that outperforms the standard FedAvg method, validated by empirical results in a competitive challenge.

Findings

Achieved top performance in MICCAI FETS 2021 challenge

Improved segmentation accuracy over FedAvg

Validated effectiveness of the new aggregation method

Abstract

We propose a simple new aggregation strategy for federated learning that won the MICCAI Federated Tumor Segmentation Challenge 2021 (FETS), the first ever challenge on Federated Learning in the Machine Learning community. Our method addresses the problem of how to aggregate multiple models that were trained on different data sets. Conceptually, we propose a new way to choose the weights when averaging the different models, thereby extending the current state of the art (FedAvg). Empirical validation demonstrates that our approach reaches a notable improvement in segmentation performance compared to FedAvg.