FedPIDAvg: A PID controller inspired aggregation method for Federated Learning

04/24/2023

∙

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.

READ FULL TEXT

FedPIDAvg: A PID controller inspired aggregation method for Federated Learning

FedCostWAvg: A new averaging for better Federated Learning

Regularized Weight Aggregation in Networked Federated Learning for Glioblastoma Segmentation

Robust Learning Protocol for Federated Tumor Segmentation Challenge

Precision-Weighted Federated Learning

Leveraging Learning Metrics for Improved Federated Learning

Federated Learning Robust to Byzantine Attacks: Achieving Zero Optimality Gap

FedDBL: Communication and Data Efficient Federated Deep-Broad Learning for Histopathological Tissue Classification

FedPIDAvg: A PID controller inspired aggregation method for Federated Learning

Related Research

FedCostWAvg: A new averaging for better Federated Learning

Regularized Weight Aggregation in Networked Federated Learning for Glioblastoma Segmentation

Robust Learning Protocol for Federated Tumor Segmentation Challenge

Precision-Weighted Federated Learning

Leveraging Learning Metrics for Improved Federated Learning

Federated Learning Robust to Byzantine Attacks: Achieving Zero Optimality Gap

FedDBL: Communication and Data Efficient Federated Deep-Broad Learning for Histopathological Tissue Classification