Research map / Continual learning / Online and replay-based
Task Relevance-Driven Prompt Expansion for Federated Continual Learning
Jiahua Dong, Wenqi Liang, Yang Cong, Yichen Li, Hongyuan Yu, Henghui Ding, Yulun Zhang, Salman Khan, Fahad Shahbaz Khan
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 TRPE instead of HiDe-Prompt + FL | FCL on CIFAR-100, Sup-21K, T=5 · CIFAR-100 | FAA: 88.44 vs 80.52 (Imp. 7.92) | Improved |
| use TRPE instead of HiDe-Prompt + FL | FCL on CIFAR-100, DINO-1K, T=20 · CIFAR-100 | FAA: 79.55 vs 78.67 (Imp. 0.88) | Improved |
| use TRPE instead of HiDe-Prompt + FL | FCL on CUB-200, Sup-21K, T=20 · CUB-200 | FAA: 83.35 vs 82.05 (Imp. 1.30) | Improved |
| use TRPE (rehearsal-free) instead of GLFC with 500 exemplars | FCL on CIFAR-100, Sup-21K, T=10 · CIFAR-100 | FAA: 87.64 vs 45.84 | Improved |
| use TRPE instead of PIP | FCL on CIFAR-100, Sup-21K, T=10 · CIFAR-100 | CAA: 76.04 vs 74.80 | Improved |
| use TRPE instead of HFC + FL | FCL on CUB-200, iBOT-1K, T=10 · CUB-200 | CAA: 65.92 vs 63.15 | Improved |
| use TRPE instead of HiDe-Prompt + FL | FCL on CUB-200, DINO-1K, T=10 · CUB-200 | CAA: 60.57 vs 59.56 | Improved |
| replace DualPrompt with HiDe-Prompt as prompt-based continual learner under FL | FCL on CIFAR-100, Sup-21K, T=5 · CIFAR-100 | FAA: 71.35 -> 80.52 | Improved |
Closest papers by meaning
- C$^2$Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning (NeurIPS 2025 · similarity 0.89)
- Federated Continual Learning via Prompt-based Dual Knowledge Transfer (ICML 2024 · similarity 0.88)
- Accurate Forgetting for Heterogeneous Federated Continual Learning (ICLR 2024 · similarity 0.87)
- Learning to Prompt Knowledge Transfer for Open-World Continual Learning (AAAI 2024 · similarity 0.86)
- Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning (ICLR 2024 · similarity 0.86)
- Scalable Language Model with Generalized Continual Learning (ICLR 2024 · similarity 0.86)
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.
