paper-with-me

홈 › Papers

Federated Noisy Client Learning

2021-06-24 · Kahou Tam, Li Li, Bo Han, Chengzhong Xu, Huazhu Fu

Federated learning (FL) collaboratively trains a shared global model depending on multiple local clients, while keeping the training data decentralized in order to preserve data privacy. However, standard FL methods ignore the noisy client issue, which may harm the overall performance of the shared model. We first investigate critical issue caused by noisy clients in FL and quantify the negative impact of the noisy clients in terms of the representations learned by different layers. We have the following two key observations: (1) the noisy clients can severely impact the convergence and performance of the global model in FL, and (2) the noisy clients can induce greater bias in the deeper layers than the former layers of the global model. Based on the above observations, we propose Fed-NCL, a framework that conducts robust federated learning with noisy clients. Specifically, Fed-NCL first identifies the noisy clients through well estimating the data quality and model divergence. Then robust layer-wise aggregation is proposed to adaptively aggregate the local models of each client to deal with the data heterogeneity caused by the noisy clients. We further perform the label correction on the noisy clients to improve the generalization of the global model. Experimental results on various datasets demonstrate that our algorithm boosts the performances of different state-of-the-art systems with noisy clients. Our code is available on https://github.com/TKH666/Fed-NCL

📄 PDF Abstract BibTeX arXiv:2106.13239

Code (1)

tkh666/fed-ncl 공식 구현 pytorch

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Federated Learning Client Pruning for Noisy Labels

2024-11-11 · Mahdi Morafah, Hojin Chang, Chen Chen, Bill Lin

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-c…

Federated Learning

Local K-Similarity Constraint for Federated Learning with Label Noise

2025-11-09 · Sanskar Amgain, Prashant Shrestha, Bidur Khanal, Alina Devkota 외 arxiv

Federated learning on clients with noisy labels is a challenging problem, as such clients can infiltrate the global model, impacting the overall generalizability of the system. Existing methods proposed to handle noisy c…

Medical Image ClassificationFederated Learning

FedSIR: Spectral Client Identification and Relabeling for Federated Learning with Noisy Labels

2026-04-22 · Sina Gholami, Abdulmoneam Ali, Tania Haghighi, Ahmed Arafa 외 arxiv

Federated learning (FL) enables collaborative model training without sharing raw data; however, the presence of noisy labels across distributed clients can severely degrade the learning performance. In this paper, we pro…

Knowledge DistillationFederated Learning

Robust Federated Learning With Noisy and Heterogeneous Clients

2022-01-01 · CVPR 2022 1 · Xiuwen Fang, Mang Ye

Model heterogeneous federated learning is a challenging task since each client independently designs its own model. Due to the annotation difficulty and free-riding participant issue, the local client usually contain…

Federated Learning

FedCorr: Multi-Stage Federated Learning for Label Noise Correction

2022-04-10 · CVPR 2022 1 · Jingyi Xu, Zihan Chen, Tony Q. S. Quek, Kai Fong Ernest Chong

Federated learning (FL) is a privacy-preserving distributed learning paradigm that enables clients to jointly train a global model. In real-world FL implementations, client data could have label noise, and different clie…

Federated LearningPrivacy Preserving