FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yoon, Taehwan, Choi, Bongjun, De Neve, Wesley
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911622098845696
author Yoon, Taehwan
Choi, Bongjun
De Neve, Wesley
author_facet Yoon, Taehwan
Choi, Bongjun
De Neve, Wesley
contents Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. However, data and system heterogeneity often cause catastrophic forgetting and unbounded drift in model updates, leading to degraded predictive performance and increased client-side computation. To address these challenges, we propose FedRef, a Bayesian fine-tuning method that leverages a reference model constructed from previous global models. FedRef integrates a MAP-based regularization term that calibrates global model updates toward a temporally aggregated reference model, thereby mitigating catastrophic forgetting and improving update stability. Unlike prior approaches, FedRef performs all fine-tuning operations on the server side, reducing client-side computational overhead while maintaining effective global optimization. Experiments on image classification (FEMNIST, CINIC-10) and medical image segmentation (FeTS2022) demonstrate that FedRef achieves superior predictive performance and faster convergence under heterogeneous, non-IID settings, while significantly lowering client-side computation compared with existing methods. These results highlight FedRef as an efficient and robust optimization framework for real-world FL scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23210
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning
Yoon, Taehwan
Choi, Bongjun
De Neve, Wesley
Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
Federated learning (FL) enables collaborative model training across distributed clients while preserving data privacy. However, data and system heterogeneity often cause catastrophic forgetting and unbounded drift in model updates, leading to degraded predictive performance and increased client-side computation. To address these challenges, we propose FedRef, a Bayesian fine-tuning method that leverages a reference model constructed from previous global models. FedRef integrates a MAP-based regularization term that calibrates global model updates toward a temporally aggregated reference model, thereby mitigating catastrophic forgetting and improving update stability. Unlike prior approaches, FedRef performs all fine-tuning operations on the server side, reducing client-side computational overhead while maintaining effective global optimization. Experiments on image classification (FEMNIST, CINIC-10) and medical image segmentation (FeTS2022) demonstrate that FedRef achieves superior predictive performance and faster convergence under heterogeneous, non-IID settings, while significantly lowering client-side computation compared with existing methods. These results highlight FedRef as an efficient and robust optimization framework for real-world FL scenarios.
title FedRef: Bayesian Fine-Tuning using a Reference Model to Mitigate Catastrophic Forgetting for Heterogeneous Federated Learning
topic Machine Learning
Artificial Intelligence
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2506.23210