Robust Learning Protocol for Federated Tumor Segmentation Challenge

TL;DR

This paper introduces RoLePRO, a robust federated learning protocol designed for tumor segmentation, addressing data heterogeneity and communication challenges through adaptive optimization and strategic parameter aggregation.

Contribution

It presents a novel two-phase federated learning protocol combining adaptive optimization and reweighted aggregation for improved tumor segmentation.

Findings

Enhanced model robustness in federated tumor segmentation

Effective handling of data heterogeneity among collaborators

Improved communication efficiency during training

Abstract

In this work, we devise robust and efficient learning protocols for orchestrating a Federated Learning (FL) process for the Federated Tumor Segmentation Challenge (FeTS 2022). Enabling FL for FeTS setup is challenging mainly due to data heterogeneity among collaborators and communication cost of training. To tackle these challenges, we propose Robust Learning Protocol (RoLePRO) which is a combination of server-side adaptive optimisation (e.g., server-side Adam) and judicious parameter (weights) aggregation schemes (e.g., adaptive weighted aggregation). RoLePRO takes a two-phase approach, where the first phase consists of vanilla Federated Averaging, while the second phase consists of a judicious aggregation scheme that uses a sophisticated reweighting, all in the presence of an adaptive optimisation algorithm at the server. We draw insights from extensive experimentation to tune learning rates for the two phases.