FB-NLL: A Feature-Based Approach to Tackle Noisy Labels in Personalized Federated Learning

TL;DR

FB-NLL introduces a feature-based, label-agnostic clustering method for personalized federated learning that effectively handles noisy labels and reduces computational costs.

Contribution

The paper proposes a novel geometry-aware, one-shot clustering approach and a feature-consistency correction strategy to improve robustness against noisy labels in PFL.

Findings

Outperforms state-of-the-art methods in accuracy across multiple datasets.

Effectively detects and corrects noisy labels without estimating noise transition matrices.

Reduces communication and computational costs with one-shot clustering.

Abstract

Personalized Federated Learning (PFL) aims to learn multiple task-specific models rather than a single global model across heterogeneous data distributions. Existing PFL approaches typically rely on iterative optimization-such as model update trajectories-to cluster users that need to accomplish the same tasks together. However, these learning-dynamics-based methods are inherently vulnerable to low-quality data and noisy labels, as corrupted updates distort clustering decisions and degrade personalization performance. To tackle this, we propose FB-NLL, a feature-centric framework that decouples user clustering from iterative training dynamics. By exploiting the intrinsic heterogeneity of local feature spaces, FB-NLL characterizes each user through the spectral structure of the covariances of their feature representations and leverages subspace similarity to identify task-consistent user groupings. This geometry-aware clustering is label-agnostic and is performed in a one-shot manner prior to training, significantly reducing communication overhead and computational costs compared to iterative baselines. Complementing this, we introduce a feature-consistency-based detection and correction strategy to address noisy labels within clusters. By leveraging directional alignment in the learned feature space and assigning labels based on class-specific feature subspaces, our method mitigates corrupted supervision without requiring estimation of stochastic noise transition matrices. In addition, FB-NLL is model-independent and integrates seamlessly with existing noise-robust training techniques. Extensive experiments across diverse datasets and noise regimes demonstrate that our framework consistently outperforms state-of-the-art baselines in terms of average accuracy and performance stability.