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

arXiv: https://arxiv.org/abs/2604.19729 · HTML: https://mlsanity.com/paper/2604.19729/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Federated Multi-Task Learning](https://mlsanity.com/paper/1705.10467/) (2017)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels](https://mlsanity.com/paper/1712.05055/) (2017)
- [An Efficient Framework for Clustered Federated Learning](https://mlsanity.com/paper/2006.04088/) (2020)
- [Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints](https://mlsanity.com/paper/1910.01991/) (2019)
- [Towards Personalized Federated Learning](https://mlsanity.com/paper/2103.00710/) (2021)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [Deep Learning is Robust to Massive Label Noise](https://mlsanity.com/paper/1705.10694/) (2017)
- [FINE Samples for Learning with Noisy Labels](https://mlsanity.com/paper/2102.11628/) (2021)
- [Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization](https://mlsanity.com/paper/2102.02414/) (2021)
- [FedCorr: Multi-Stage Federated Learning for Label Noise Correction](https://mlsanity.com/paper/2204.04677/) (2022)
- [Robust Federated Learning with Noisy Labels](https://mlsanity.com/paper/2012.01700/) (2020)
- [Mitigating Memorization of Noisy Labels by Clipping the Model Prediction](https://mlsanity.com/paper/2212.04055/) (2022)
- [FedNoRo: Towards Noise-Robust Federated Learning by Addressing Class Imbalance and Label Noise Heterogeneity](https://mlsanity.com/paper/2305.05230/) (2023)
- [Towards Federated Learning against Noisy Labels via Local Self-Regularization](https://mlsanity.com/paper/2208.12807/) (2022)
- [Fundamentals of Task-Agnostic Data Valuation](https://mlsanity.com/paper/2208.12354/) (2022)
- [CTRL: Clustering Training Losses for Label Error Detection](https://mlsanity.com/paper/2208.08464/) (2022)
- [FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels](https://mlsanity.com/paper/2312.12263/) (2023)
- [Federated Learning with Extremely Noisy Clients via Negative Distillation](https://mlsanity.com/paper/2312.12703/) (2023)
- [Federated Learning Client Pruning for Noisy Labels](https://mlsanity.com/paper/2411.07391/) (2024)
- [Data Similarity-Based One-Shot Clustering for Multi-Task Hierarchical Federated Learning](https://mlsanity.com/paper/2410.02733/) (2024)
- [RCC-PFL: Robust Client Clustering under Noisy Labels in Personalized Federated Learning](https://mlsanity.com/paper/2503.19886/) (2025)

## Built on by (most cited first, 2 of 2)

- [Eigenspace-Based Clustering for Personalized System Identification](https://mlsanity.com/paper/2606.20811/) (2026)
- [OCT-FedSIR: Toward Trustworthy Federated Ophthalmic Learning under Annotation Noise](https://mlsanity.com/paper/2609.14734/) (2026)

## Abstract (arXiv)

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.