Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Continual Learning with Weighted Inter-client Transfer
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 |
|---|---|---|---|
| Adding weighted inter-client transfer of task-adaptive parameters with decomposed FedWeIT model (vs. naive FedProx-APD aggregation) | FedWeIT · NonIID-50, LeNet, 5 clients | Accuracy: 84.11 vs 81.20 (FedProx-APD) | Helped |
| Using FedWeIT decomposition and transfer vs. FedProx-APD | FedWeIT · Overlapped-CIFAR-100, LeNet, 5 clients | Accuracy: 55.16 vs 52.20 | Helped |
| Naive federated aggregation (FedProx) on top of continual learning baselines | FedProx-based FCL · NonIID-50, LeNet, 5 clients | Accuracy: 68.03 vs 81.42 (APD local) | Hurt |
| Federated aggregation with FedProx vs. local EWC/Stable-SGD/APD | FedProx-APD · Overlapped-CIFAR-100, LeNet, 5 clients | Accuracy: 52.20 vs 50.82 (APD) | Mixed |
| Adding FedWeIT on ResNet-18 vs. APD baseline | FedWeIT ResNet-18 · NonIID-50, ResNet-18 | Accuracy: 94.86 vs 92.89 (FedProx-APD) | Helped |
| Scaffold regularization for FCL | Scaffold · NonIID-50, LeNet, 5 clients | Accuracy: 30.84 vs 68.03 (FedProx) | Hurt |
| Sparse communication: FedWeIT C2S cost reduced vs FedProx baselines | FedWeIT · NonIID-50, LeNet, 5 clients | Client to Server Cost: 0.37 vs 1.22 | Helped |
Closest papers by meaning
- Federated Continual Learning via Prompt-based Dual Knowledge Transfer (ICML 2024 · similarity 0.88)
- Traceable Federated Continual Learning (CVPR 2024 · similarity 0.87)
- Accurate Forgetting for Heterogeneous Federated Continual Learning (ICLR 2024 · similarity 0.86)
- HERO: A Heterogeneity-Aware Benchmark Library for Federated Continual Learning (NeurIPS 2026 · similarity 0.86)
- Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning (ICLR 2024 · similarity 0.86)
- Decentralized Dynamic Cooperation of Personalized Models for Federated Continual Learning (NeurIPS 2025 · 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.