FedPIDAvg: A PID controller inspired aggregation method for Federated Learning

TL;DR

FedPIDAvg introduces a novel aggregation method for federated learning inspired by PID controllers, effectively handling data heterogeneity and improving performance in tumor segmentation tasks.

Contribution

The paper proposes FedPIDAvg, an improved federated learning aggregation strategy that incorporates PID control principles and models data center sizes for better performance.

Findings

Outperformed all other submissions in FETS22.

Effectively manages data heterogeneity across centers.

Incorporates PID control principles into federated learning aggregation.

Abstract

This paper presents FedPIDAvg, the winning submission to the Federated Tumor Segmentation Challenge 2022 (FETS22). Inspired by FedCostWAvg, our winning contribution to FETS21, we contribute an improved aggregation strategy for federated and collaborative learning. FedCostWAvg is a weighted averaging method that not only considers the number of training samples of each cluster but also the size of the drop of the respective cost function in the last federated round. This can be interpreted as the derivative part of a PID controller (proportional-integral-derivative controller). In FedPIDAvg, we further add the missing integral term. Another key challenge was the vastly varying size of data samples per center. We addressed this by modeling the data center sizes as following a Poisson distribution and choosing the training iterations per center accordingly. Our method outperformed all other submissions.