Research map / Federated learning and privacy / Personalized and heterogeneous FL
Cross-task Calibration for Asynchronous Federated Continual Learning
Yichen Li, Haozhao Wang, Hang Su, Yulong Li, Xiaoquan Yi, Yankai Jiang, Chuang Zhao, Imran Razzak, Ruixuan Li
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 C2-AFCL instead of FedSpace | asynchronous FCL · CIFAR100 | average accuracy: 38.61 -> 42.57 | Improved |
| use C2-AFCL instead of FedSpace | asynchronous FCL · Office31 | average accuracy: 47.61 -> 50.54 | Improved |
| use C2-AFCL instead of FedSpace | asynchronous FCL · Office-Caltech-10 | forgetting score: 23.72 -> 20.32 | Improved |
| add intra-client calibration (ablation) | C2-AFCL · CIFAR100 and Office31 (alpha=1) | average accuracy | Improved |
| add inter-task orthogonal calibration (ablation) | C2-AFCL · CIFAR100 and Office31 (alpha=1) | forgetting score | Improved |
| add C2-AFCL calibration | asynchronous FCL · communication rounds CIFAR100 | rounds to best accuracy: 877 (FedSpace) vs 856 | No clear effect |
| reduce client selection ratio r (ablation) | C2-AFCL · CIFAR100 and Office31 | accuracy | No clear effect |
| vary Dirichlet alpha and staleness | C2-AFCL · CIFAR100 | accuracy | No clear effect |
Closest papers by meaning
- HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning (NeurIPS 2026 · similarity 0.90)
- Traceable Federated Continual Learning (CVPR 2024 · similarity 0.88)
- Accurate Forgetting for Heterogeneous Federated Continual Learning (ICLR 2024 · similarity 0.88)
- C$^2$Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning (NeurIPS 2025 · similarity 0.88)
- Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor (CVPR 2025 · similarity 0.88)
- Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning (NeurIPS 2025 · 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.
