Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedPKDA: Personalized Federated Learning with Privacy-Preserving Knowledge Dynamic Alignment
Moxuan Zeng, Wenxuan Tu, Yuanyi Chen, Yiying Wang, Miao Yu, Xiangyan Tang, Jieren Cheng
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 |
|---|---|---|---|
| add knowledge dynamic alignment (KDA) (ablation) | Base · Cifar100 (beta=0.3, P=0.2) | accuracy: 41.55 -> 43.84 | Improved |
| add cross-client prototypes (CP) (ablation) | Base · Cifar100 (beta=0.3, P=0.2) | accuracy: 41.55 -> 43.20 | Improved |
| add KDA (ablation) | Base · Flowers102 (beta=0.3, P=0.2) | accuracy: 39.49 -> 40.71 | Improved |
| add cross-client prototypes (ablation) | Base · Flowers102 (beta=0.3, P=0.2) | accuracy: 39.49 -> 40.60 | Improved |
| combine KDA and CP (ablation) | w/ KDA · Flowers102 (beta=0.3, P=0.2) | accuracy: 40.71 -> 44.11 | Improved |
| combine KDA and CP (ablation) | w/ CP · Cifar100 (beta=0.3, P=0.2) | accuracy: 43.20 -> 44.91 | Improved |
| use FedPKDA instead of FedAS | FedAS · Cifar100 (beta=0.3, P=0.2) | accuracy: 40.68 -> 44.91 | Improved |
| use FedPKDA instead of FedAS | FedAS · Flowers102 (beta=0.5, P=0.2) | accuracy: 27.90 -> 38.09 | Improved |
| add noised prototype sharing | FedAvg-P · Cifar100 DLG attack | PSNR: 7.41 -> 6.98 | Improved |
| increase local alignment weight (ablation) | FedPKDA · Cifar100 (beta=0.5) | accuracy | Improved |
| increase global alignment weight (ablation) | FedPKDA · Cifar100 (beta=0.5) | accuracy | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FedAS — FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024) · better on 4 of 4 shared results
- FedBABU — FedBABU: Toward Enhanced Representation for Federated Image Classification (ICLR 2022) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.90)
- FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity (ICLR 2024 · similarity 0.90)
- FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees (ICML 2024 · similarity 0.89)
- FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024 · similarity 0.88)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.88)
- Little Is Enough: Boosting Privacy by Sharing Only Hard Labels in Federated Semi-Supervised Learning (AAAI 2025 · 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.
