Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Learning with Local Openset Noisy Labels
Zonglin Di, Zhaowei Zhu, Xiaoxiao Li, Yang Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add globally shared DP contrastive labels (FedDPCont) to FedAvg | FedAvg · CIFAR-10 symmetric noise 0.2 | accuracy: 76.84 -> 84.77 | Improved |
| add globally shared DP contrastive labels (FedDPCont) to FedAvg | FedAvg · CIFAR-10 random noise 0.4 | accuracy: 59.19 -> 72.69 | Improved |
| apply centralized noisy-label methods (loss correction, Co-teaching, T-revision) locally in FL | FedAvg · CIFAR-10 | accuracy: 76.84 -> 79.14 (LC, symmetric 0.2) | No clear effect |
| vary label DP level epsilon from 0.01 to 100 versus no DP (ablation) | FedDPCont · CIFAR-10 random noise 0.4 | accuracy: 74.03 (No DP) vs 72.44 (epsilon 0.81) | No clear effect |
| replace DivideMix with FedDPCont on CIFAR-10 symmetric 0.2 | DivideMix · CIFAR-10 symmetric noise 0.2 | accuracy: 79.28 -> 84.77 | Improved |
| use FedDPCont instead of DivideMix on CIFAR-10 symmetric | DivideMix · CIFAR-10 symmetric noise | training time (hr): 22.33 -> 4.17 | Improved |
| use FedDPCont instead of DivideMix at high noise on CIFAR-100 | DivideMix · CIFAR-100 symmetric noise 0.8 | accuracy: 19.87 -> 14.04 | Hurt |
| use FedDPCont instead of FedCorr on CIFAR-100 | FedCorr · CIFAR-100 symmetric noise 0.2 | accuracy: 57.65 -> 58.55 | Improved |
| use FedDPCont on real-world Clothing-1M instead of FedAvg | FedAvg · Clothing-1M | accuracy: 70.27 -> 70.88 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FedCorr — FedCorr: Multi-Stage Federated Learning for Label Noise Correction (CVPR 2022) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FedDiv: Collaborative Noise Filtering for Federated Learning with Noisy Labels (AAAI 2024 · similarity 0.91)
- Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning (AAAI 2025 · similarity 0.91)
- FedFixer: Mitigating Heterogeneous Label Noise in Federated Learning (AAAI 2024 · similarity 0.90)
- (FL)$^2$: Overcoming Few Labels in Federated Semi-Supervised Learning (NeurIPS 2024 · similarity 0.90)
- FedClean: A General Robust Label Noise Correction for Federated Learning (ICML 2025 · similarity 0.89)
- Federated Learning with Extremely Noisy Clients via Negative Distillation (AAAI 2024 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
