Research map / Federated learning and privacy / Personalized and heterogeneous FL
Rethinking Federated Learning With Domain Shift: A Prototype View
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 CPCL using cluster prototypes (ablation) | FedAvg · Digits | Top-1 accuracy | Helped |
| Add CPCL using cluster prototypes (ablation) | FedAvg · Office Caltech | Top-1 accuracy | Helped |
| Add UPCR using unbiased prototypes (ablation) | FedAvg · Digits | Top-1 accuracy | Helped |
| Add UPCR using unbiased prototypes (ablation) | FedAvg · Office Caltech | Top-1 accuracy | Helped |
| Combine CPCL and UPCR (ablation) | FedAvg · Digits | Top-1 accuracy | Helped |
| Combine CPCL and UPCR (ablation) | FedAvg · Office Caltech | Top-1 accuracy | Helped |
| Replace global prototypes with cluster prototypes in CPCL (ablation) | CPCL · Digits | Top-1 accuracy: +0.62 | Helped |
| Replace global prototypes with cluster prototypes in CPCL (ablation) | CPCL · Office Caltech | Top-1 accuracy: +2.08 | Helped |
| Replace global prototypes with unbiased prototypes for consistent regularization (ablation) | FPL · Digits | Top-1 accuracy: +0.82 | Helped |
| Replace global prototypes with unbiased prototypes for consistent regularization (ablation) | FPL · Office Caltech | Top-1 accuracy: +0.73 | Helped |
| Use FPL instead of FedProto | federated learning · Digits | Top-1 accuracy: +2.98 | Helped |
| Use FPL instead of FedProto | federated learning · Office Caltech | Top-1 accuracy: +4.59% | Helped |
Closest papers by meaning
- Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains (NeurIPS 2024 · similarity 0.91)
- Federated Graph Learning under Domain Shift with Generalizable Prototypes (AAAI 2024 · similarity 0.90)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.89)
- FedWon: Triumphing Multi-domain Federated Learning Without Normalization (ICLR 2024 · similarity 0.89)
- FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation (NeurIPS 2024 · similarity 0.88)
- Beyond Federated Prototype Learning: Learnable Semantic Anchors with Hyperspherical Contrast for Domain-Skewed Data (AAAI 2025 · 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.