Research map / Continual learning / Class-incremental
Federated Class-Incremental Learning
Check 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 |
|---|---|---|---|
| Use GLFC instead of PODNet + FL | Federated class-incremental learning · CIFAR-100, 10 tasks | average accuracy: 59.7 -> 66.9 | Helped |
| Use GLFC instead of PODNet + FL | Federated class-incremental learning · ImageNet-Subset, 10 tasks | average accuracy: 52.6 -> 57.0 | Helped |
| Use GLFC instead of PODNet + FL | Federated class-incremental learning · TinyImageNet, 10 tasks | average accuracy: 44.6 -> 47.9 | Helped |
| Add class-aware gradient compensation (ablation) | GLFC · CIFAR-100, 10 tasks | average accuracy: 60.1 -> 66.9 | Helped |
| Add class-semantic relation distillation (ablation) | GLFC · CIFAR-100, 10 tasks | average accuracy: 65.8 -> 66.9 | Helped |
| Add proxy server (ablation) | GLFC · CIFAR-100, 10 tasks | average accuracy: 64.6 -> 66.9 | Helped |
| Add class-aware gradient compensation (ablation) | GLFC · ImageNet-Subset, 10 tasks | average accuracy: 55.1 -> 57.0 | Helped |
| Add class-semantic relation distillation (ablation) | GLFC · ImageNet-Subset, 10 tasks | average accuracy: 47.3 -> 57.0 | Helped |
| Add proxy server (ablation) | GLFC · ImageNet-Subset, 10 tasks | average accuracy: 52.8 -> 57.0 | Helped |
| Add class-aware gradient compensation (ablation) | GLFC · TinyImageNet, 20 tasks, first 10 tasks | average accuracy: 52.1 -> 54.9 | Helped |
| Add class-semantic relation distillation (ablation) | GLFC · TinyImageNet, 20 tasks, first 10 tasks | average accuracy: 44.8 -> 54.9 | Helped |
| Add proxy server (ablation) | GLFC · TinyImageNet, 20 tasks, first 10 tasks | average accuracy: 50.3 -> 54.9 | Helped |
Closest papers by meaning
- Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting (ICLR 2025 · similarity 0.92)
- Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning (ICLR 2024 · similarity 0.89)
- Class-wise Balancing Data Replay for Federated Class-Incremental Learning (NeurIPS 2025 · similarity 0.89)
- C$^2$Prompt: Class-aware Client Knowledge Interaction for Federated Continual Learning (NeurIPS 2025 · similarity 0.88)
- Accurate Forgetting for Heterogeneous Federated Continual Learning (ICLR 2024 · similarity 0.87)
- Splitting with Importance-aware Updating for Heterogeneous Federated Learning with Large Language Models (ICML 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.