DFedReweighting: A Unified Framework for Objective-Oriented Reweighting in Decentralized Federated Learning

TL;DR

DFedReweighting introduces a unified reweighting framework for decentralized federated learning, enhancing fairness and robustness by customizing client aggregation weights based on target performance metrics.

Contribution

It proposes a novel objective-oriented reweighting method that guarantees convergence and improves fairness and robustness in decentralized federated learning.

Findings

Significant improvement in fairness and Byzantine robustness demonstrated.

Theoretical proof of linear convergence under certain conditions.

Flexible framework accommodating diverse learning objectives.

Abstract

Decentralized federated learning (DFL) has emerged as a promising paradigm that enables multiple clients to collaboratively train machine learning models through iterative rounds of local training, communication, and aggregation, without relying on a central server. Nevertheless, DFL systems continue to face a range of challenges, including fairness and Byantine robustness. To address these challenges, we propose \textbf{DFedReweighting}, a unified aggregation framework that achieves diverse learning objectives in DFL via objective-oriented reweighting at the final step of each learning round. Specifically, for each client, the framework first evaluates a target performance metric (TPM) on a compact auxiliary dataset constructed from local data, yielding preliminary aggregation weights, which are subsequently refined by a customized reweighting strategy (CRS) to produce the final aggregation weights. Theoretically, we prove that an appropriate TPM-CRS combination guarantees linear convergence for general $L$-smoothand strongly convex functions. Empirical results consistently demonstrate that \textbf{DFedReweighting} significantly improves fairness and robustness against Byzantine attacks across diverse settings. Two multi-objective examples, spanning tasks across and within clients, further establish that a broad range of desired learning objectives can be accommodated by appropriately designing the TPM and CRS. Our code is available at https://github.com/KaichuangZhang/DFedReweighting.