Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedGain: Toward Negative-Gain-Free Client Collaboration in Federated Learning
Yuqing Zhang, Changli Zhou, Binghuang Huang, Hui Tian
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 FedGain collaboration structure to FedAvg | FedAvg · FMNIST (Label Shift) | accuracy: 46.62 -> 90.16 | Improved |
| add FedGain to FedAvg | FedAvg · CIFAR10 (Feature Shift) | accuracy: 44.74 -> 50.44 | Improved |
| add FedGain to FedAvg | FedAvg · CIFAR100 (Quality Shift) | accuracy: 26.27 -> 37.95 | Improved |
| add FedGain to personalized FL (pFedMe) | pFedMe · CIFAR10 (Feature Shift) | accuracy: 38.00 -> 47.48 | Improved |
| add FedGain to FedAS and FedCSD on FMNIST | FedAS, FedCSD · FMNIST (Label Shift) | NGP: FedAS 70.00 -> 5.00; FedCSD 65.00 -> 17.50 | Mixed |
| add FedGain to GFL and PFL methods on OfficeHome | FedAvg, FedProx, Ditto, etc. · OfficeHome (Domain Shift) | NGP: FedAvg 25.00 -> 0.00 | Improved |
| use FedGain clustering instead of IFCA, FedCluster, FeSEM, CFL-GP | clustered FL with FedAvg · CIFAR100 (Quality Shift) | accuracy: 29.78 (FeSEM, best baseline) -> 37.95 | Improved |
| use FedGain clustering vs FedCluster on FMNIST | clustered FL with FedAvg · FMNIST (Label Shift) | accuracy: 90.11 (FedCluster) -> 90.16 | No clear effect |
| use only distribution shift term (remove quantity skew) (ablation) | FedGain · FMNIST (Label Shift) | accuracy: 52.26 -> 90.16 when adding quantity term | Improved |
| use only quantity skew term (remove distribution shift) (ablation) | FedGain · CIFAR100 (Quality Shift) | accuracy: 34.44 -> 37.95 when adding distribution term | Improved |
| set kernel decay gamma to 5.0 vs 2.0 or 8.0 (ablation) | FedGain · CIFAR100 (Quality Shift) | accuracy: 31.64 (2.0), 37.95 (5.0), 36.95 (8.0) | Mixed |
| vary capacity constant C in {6, 8, 10} (ablation) | FedGain · CIFAR10/FMNIST/CIFAR100 | accuracy: CIFAR100: 34.44, 37.95, 34.49 | Mixed |
Closest papers by meaning
- FedImpro: Measuring and Improving Client Update in Federated Learning (ICLR 2024 · similarity 0.90)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.90)
- Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning (NeurIPS 2024 · similarity 0.89)
- Federated Learning with Sample-level Client Drift Mitigation (AAAI 2025 · similarity 0.89)
- Momentum Benefits Non-iid Federated Learning Simply and Provably (ICLR 2024 · similarity 0.89)
- Adaptive Federated Learning with Auto-Tuned Clients (ICLR 2024 · similarity 0.89)
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.
