Research map / Continual learning / Domain and prompt-based
Learn From Others and Be Yourself in Heterogeneous Federated 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 cross-correlation learning with unlabeled public data and dual-domain distillation during local updates | Heterogeneous federated learning · Digits, inter-domain AVG | accuracy: 31.14 -> 33.51 | Helped |
| Use cross-correlation learning with unlabeled public data and dual-domain distillation during local updates | Heterogeneous federated learning · Office-Home, inter-domain AVG | accuracy: 24.51 -> 27.88 | Helped |
| Use FCCL instead of the strongest listed baseline | Digits · SVHN intra-domain | accuracy: 79.79 -> 78.55 | Hurt |
| Use FCCL instead of the strongest listed baseline | Digits · SYN intra-domain | accuracy: 91.40 -> 91.23 | Hurt |
| Use FCCL instead of the strongest listed baseline | Office-Home · Clipart intra-domain | accuracy: 65.58 -> 65.42 | Hurt |
| Replace Cifar-100 with ImageNet as unlabeled public data (ablation) | FCCL · Digits, inter-domain AVG | accuracy: 33.51 -> 35.70 | Helped |
| Replace Cifar-100 with Fashion-MNIST as unlabeled public data (ablation) | FCCL · Digits, inter-domain AVG | accuracy: 33.51 -> 36.82 | Helped |
| Add dual-domain knowledge distillation during local updating (ablation) | FCCL · Digits, inter-domain AVG, Cifar-100 public data | accuracy: 27.13 -> 33.51 | Helped |
| Add dual-domain knowledge distillation during local updating (ablation) | FCCL · Digits, inter-domain AVG, ImageNet public data | accuracy: 30.26 -> 35.70 | Helped |
| Add dual-domain knowledge distillation during local updating (ablation) | FCCL · Digits, inter-domain AVG, Fashion-MNIST public data | accuracy: 32.42 -> 36.82 | Helped |
| Add dual-domain knowledge distillation during local updating (ablation) | FCCL · Digits, intra-domain AVG, Cifar-100 public data | accuracy: 82.07 -> 85.76 | Helped |
| Add dual-domain knowledge distillation during local updating (ablation) | FCCL · Digits, intra-domain AVG, ImageNet public data | accuracy: 82.21 -> 86.09 | Helped |
Closest papers by meaning
- Accurate Forgetting for Heterogeneous Federated Continual Learning (ICLR 2024 · similarity 0.90)
- Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning (ICLR 2024 · similarity 0.89)
- Handling Spatial-Temporal Data Heterogeneity for Federated Continual Learning via Tail Anchor (CVPR 2025 · similarity 0.88)
- Federated Learning via Input-Output Collaborative Distillation (AAAI 2024 · similarity 0.88)
- Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting (ICLR 2025 · similarity 0.88)
- Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond (ICLR 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.