FNBench: Benchmarking Robust Federated Learning against Noisy Labels

2025-05-10 · Xuefeng Jiang, Jia Li, Nannan Wu, Zhiyuan Wu, Xujing Li, Sheng Sun, Gang Xu, Yuwei Wang, Qi Li, Min Liu

Robustness to label noise within data is a significant challenge in federated learning (FL). From the data-centric perspective, the data quality of distributed datasets can not be guaranteed since annotations of different clients contain complicated label noise of varying degrees, which causes the performance degradation. There have been some early attempts to tackle noisy labels in FL. However, there exists a lack of benchmark studies on comprehensively evaluating their practical performance under unified settings. To this end, we propose the first benchmark study FNBench to provide an experimental investigation which considers three diverse label noise patterns covering synthetic label noise, imperfect human-annotation errors and systematic errors. Our evaluation incorporates eighteen state-of-the-art methods over five image recognition datasets and one text classification dataset. Meanwhile, we provide observations to understand why noisy labels impair FL, and additionally exploit a representation-aware regularization method to enhance the robustness of existing methods against noisy labels based on our observations. Finally, we discuss the limitations of this work and propose three-fold future directions. To facilitate related communities, our source code is open-sourced at https://github.com/Sprinter1999/FNBench.

📄 PDF Abstract BibTeX arXiv:2505.06684

Code (1)

sprinter1999/fnbench 공식 구현 pytorch

Tasks

Benchmarking Federated Learning text-classification Text Classification

FedNoisy: Federated Noisy Label Learning Benchmark

2023-06-20 · Siqi Liang, Jintao Huang, Junyuan Hong, Dun Zeng 외

Federated learning has gained popularity for distributed learning without aggregating sensitive data from clients. But meanwhile, the distributed and isolated nature of data isolation may be complicated by data quality, …

Federated Learning Learning with noisy labels

Towards Federated Learning against Noisy Labels via Local Self-Regularization

2022-08-25 · Xuefeng Jiang, Sheng Sun, Yuwei Wang, Min Liu

Federated learning (FL) aims to learn joint knowledge from a large scale of decentralized devices with labeled data in a privacy-preserving manner. However, since high-quality labeled data require expensive human intelli…

Federated Learning Privacy Preserving

FedCova: Robust Federated Covariance Learning Against Noisy Labels

2026-03-04 · Xiangyu Zhong, Xiaojun Yuan, Ying-Jun Angela Zhang arxiv

Noisy labels in distributed datasets induce severe local overfitting and consequently compromise the global model in federated learning (FL). Most existing solutions rely on selecting clean devices or aligning with publi…

Federated Learning

Federated Medical Image Segmentation under Real-World Label Noise: A Benchmark Suite for Noisy Label Learning Method Selection

2026-06-15 · Markus Bujotzek, Dimitrios Bounias, Stefan Denner, Ralf Floca 외 arxiv

While federated learning (FL) enables collaborative medical image segmentation without centralizing sensitive data, real-world deployment is frequently complicated by cross-site label imperfections such as contour disagr…

Medical Image Segmentation Federated Learning

FedEFC: Federated Learning Using Enhanced Forward Correction Against Noisy Labels

2025-04-08 · Seunghun Yu, Jin-Hyun Ahn, Joonhyuk Kang

Federated Learning (FL) is a powerful framework for privacy-preserving distributed learning. It enables multiple clients to collaboratively train a global model without sharing raw data. However, handling noisy labels in…