Federated Learning Client Pruning for Noisy Labels

TL;DR

This paper proposes ClipFL, a federated learning framework that improves robustness against noisy labels by identifying and excluding noisy clients based on their performance, leading to better accuracy and efficiency.

Contribution

ClipFL introduces a novel client pruning method using Noise Candidacy Score to effectively handle noisy labels in federated learning environments.

Findings

Achieves accurate noisy client identification.

Outperforms state-of-the-art FL methods in accuracy.

Reduces communication costs and accelerates convergence.

Abstract

Federated Learning (FL) enables collaborative model training across decentralized edge devices while preserving data privacy. However, existing FL methods often assume clean annotated datasets, impractical for resource-constrained edge devices. In reality, noisy labels are prevalent, posing significant challenges to FL performance. Prior approaches attempt label correction and robust training techniques but exhibit limited efficacy, particularly under high noise levels. This paper introduces ClipFL (Federated Learning Client Pruning), a novel framework addressing noisy labels from a fresh perspective. ClipFL identifies and excludes noisy clients based on their performance on a clean validation dataset, tracked using a Noise Candidacy Score (NCS). The framework comprises three phases: pre-client pruning to identify potential noisy clients and calculate their NCS, client pruning to exclude a percentage of clients with the highest NCS, and post-client pruning for fine-tuning the global model with standard FL on clean clients. Empirical evaluation demonstrates ClipFL's efficacy across diverse datasets and noise levels, achieving accurate noisy client identification, superior performance, faster convergence, and reduced communication costs compared to state-of-the-art FL methods. Our code is available at https://github.com/MMorafah/ClipFL.