Research map / Federated learning and privacy / Personalized and heterogeneous FL
PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.
Mingjia Shi, Yuhao Zhou, Kai Wang, Huaizheng Zhang, Shudong Huang, Qing Ye, Jiancheng Lv
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 |
|---|---|---|---|
| Combine loss-gradient and memorized envelope-gradient prior selection instead of using no personalized prior (ablation) | pFedBreD · All tasks (Avg) | accuracy (%): 77.6 -> 81.5 | Improved |
| Use loss-gradient prior selection alone instead of no personalized prior (ablation) | pFedBreD · All tasks (Avg) | accuracy (%): 77.6 -> 75.3 | Hurt |
| Use memorized envelope-gradient prior selection alone instead of no personalized prior (ablation) | pFedBreD · Hard tasks (H.Avg) | accuracy (%): 65.1 -> 65.7 | No clear effect |
| Add fine-tuning after the mh personalized model | pFedBreD mh · All tasks (Avg) | accuracy (%): 81.47 -> 82.37 | Improved |
| Add aggregate momentum to the mh personalized model | pFedBreD mh · All tasks (Avg) | accuracy (%): 81.47 -> 83.09 | Improved |
| Use mh+AM rather than the strongest listed baseline | FEMNIST DNN · FEMNIST DNN | accuracy (%): 66.79 -> 70.34 | Improved |
| Use mh+AM rather than the strongest listed baseline | Sent140 LSTM · Sent140 LSTM | accuracy (%): 70.73 -> 73.68 | Improved |
Closest papers by meaning
- Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees (ICML 2025 · similarity 0.89)
- Harnessing Heterogeneous Statistical Strength for Personalized Federated Learning via Hierarchical Bayesian Inference (ICML 2025 · similarity 0.89)
- Adaptive Latent-Space Constraints in Personalized Federated Learning (NeurIPS 2025 · similarity 0.89)
- Look Back for More: Harnessing Historical Sequential Updates for Personalized Federated Adapter Tuning (AAAI 2025 · similarity 0.88)
- FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024 · similarity 0.88)
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.88)
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.
