Research map / Federated learning and privacy / Personalized and heterogeneous FL
Optimizing the Collaboration Structure in Cross-Silo Federated Learning
Wenxuan Bao, Haohan Wang, Jun Wu, Jingrui He
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 |
|---|---|---|---|
| Use FedCollab to choose the collaboration structure for FedAvg | FedAvg · FashionMNIST, label shift | accuracy: 46.64 ± 0.12 -> 92.45 ± 0.07 | Improved |
| Use FedCollab to choose the collaboration structure for FedAvg | FedAvg · CIFAR-10, feature shift | accuracy: 44.31 ± 0.98 -> 52.61 ± 0.60 | Improved |
| Use FedCollab to choose the collaboration structure for FedAvg | FedAvg · CIFAR-100, concept shift | accuracy: 26.62 ± 0.12 -> 40.94 ± 0.22 | Improved |
| Add quantity-aware client collaboration (ablation) | FedCollab · FashionMNIST, label shift | accuracy: 90.31 ± 0.11 -> 92.45 ± 0.07 | Improved |
| Add pairwise distribution-distance awareness (ablation) | FedCollab · FashionMNIST, label shift | accuracy: 67.79 ± 0.89 -> 92.45 ± 0.07 | Improved |
Closest papers by meaning
- Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning (NeurIPS 2024 · similarity 0.91)
- FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler (ICLR 2024 · similarity 0.88)
- FedCompetitors: Harmonious Collaboration in Federated Learning with Competing Participants (AAAI 2024 · similarity 0.87)
- Clustered Federated Learning via Gradient-based Partitioning (ICML 2024 · similarity 0.87)
- Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis (NeurIPS 2024 · similarity 0.87)
- Convergence Analysis of Split Federated Learning on Heterogeneous Data (NeurIPS 2024 · similarity 0.87)
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.
