Research map / Federated learning and privacy / Personalized and heterogeneous FL
Layer-Wised Model Aggregation for Personalized 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 layer-specific aggregation weights generated by client-specific hypernetworks instead of model-wide aggregation weights | Personalized federated learning · EMNIST, FashionMNIST, CIFAR10, and CIFAR100 under non-IID_1 and non-IID_2 | accuracy | Helped |
| Retain the top-weighted layer locally rather than aggregating it (ablation) | HeurpFedLA · EMNIST, 10 clients | accuracy: 90.65 -> 94.11 | Helped |
| Retain the top-weighted layers locally rather than aggregating them (ablation) | HeurpFedLA · CIFAR10, 10 clients | accuracy: 61.43 -> 60.02; 61.43 -> 59.90; 61.43 -> 59.23 | Hurt |
| Retain the top-weighted layers locally rather than aggregating them (ablation) | HeurpFedLA · EMNIST, 10 clients | communication cost: 491.08 -> 488.65; 491.08 -> 312.52 | Helped |
| Retain the top-weighted layers locally rather than aggregating them (ablation) | HeurpFedLA · CIFAR10, 10 clients | communication cost: 693.98 -> 418.97; 693.98 -> 382.25; 693.98 -> 379.82 | Helped |
Closest papers by meaning
- pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning (NeurIPS 2024 · similarity 0.92)
- FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024 · similarity 0.91)
- PeFLL: Personalized Federated Learning by Learning to Learn (ICLR 2024 · similarity 0.91)
- PFedCS: A Personalized Federated Learning Method for Enhancing Collaboration among Similar Classifiers (AAAI 2025 · similarity 0.90)
- FedCALM: Conflict-aware Layer-wise Mitigation for Selective Aggregation in Deeper Personalized Federated Learning (CVPR 2025 · similarity 0.90)
- Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian Inference (ICML 2025 · similarity 0.89)
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.