paper-with-me

홈 › Papers

FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels

2023-12-19 · Jichang Li, Guanbin Li, Hui Cheng, Zicheng Liao, Yizhou Yu

Federated learning with noisy labels (F-LNL) aims at seeking an optimal server model via collaborative distributed learning by aggregating multiple client models trained with local noisy or clean samples. On the basis of a federated learning framework, recent advances primarily adopt label noise filtering to separate clean samples from noisy ones on each client, thereby mitigating the negative impact of label noise. However, these prior methods do not learn noise filters by exploiting knowledge across all clients, leading to sub-optimal and inferior noise filtering performance and thus damaging training stability. In this paper, we present FedDiv to tackle the challenges of F-LNL. Specifically, we propose a global noise filter called Federated Noise Filter for effectively identifying samples with noisy labels on every client, thereby raising stability during local training sessions. Without sacrificing data privacy, this is achieved by modeling the global distribution of label noise across all clients. Then, in an effort to make the global model achieve higher performance, we introduce a Predictive Consistency based Sampler to identify more credible local data for local model training, thus preventing noise memorization and further boosting the training stability. Extensive experiments on CIFAR-10, CIFAR-100, and Clothing1M demonstrate that \texttt{FedDiv} achieves superior performance over state-of-the-art F-LNL methods under different label noise settings for both IID and non-IID data partitions. Source code is publicly available at https://github.com/lijichang/FLNL-FedDiv.

📄 PDF Abstract BibTeX arXiv:2312.12263

Code (1)

lijichang/flnl-feddiv 공식 구현 pytorch

Tasks

Federated LearningLearning with noisy labelsMemorization

Similar Papers 제목 키워드 기반

Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data

2025-05-14 · Alpaslan Gokcen, Ali Boyaci

Federated learning (FL) presents an effective solution for collaborative model training while maintaining data privacy across decentralized client datasets. However, data quality issues such as noisy labels, missing clas…

Federated LearningMissing LabelsSynthetic Data Generation

FedRGL: Robust Federated Graph Learning for Label Noise

2024-11-28 · De Li, Haodong Qian, Qiyu Li, Zhou Tan 외

Federated Graph Learning (FGL) is a distributed machine learning paradigm based on graph neural networks, enabling secure and collaborative modeling of local graph data among clients. However, label noise can degrade the…

Contrastive LearningGraph Learning

Diversity-Driven Learning: Tackling Spurious Correlations and Data Heterogeneity in Federated Models

2025-04-15 · Gergely D. Németh, Eros Fanì, Yeat Jeng Ng, Barbara Caputo 외

Federated Learning (FL) enables decentralized training of machine learning models on distributed data while preserving privacy. However, in real-world FL settings, client data is often non-identically distributed and imb…

AttributeDiversityFederated Learningimage-classification+1

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 SegmentationFederated Learning

Collaboratively Learning Federated Models from Noisy Decentralized Data

2024-09-03 · Haoyuan Li, Mathias Funk, Nezihe Merve Gürel, Aaqib Saeed

Federated learning (FL) has emerged as a prominent method for collaboratively training machine learning models using local data from edge devices, all while keeping data decentralized. However, accounting for the quality…

Federated Learning