Research map / Federated learning and privacy / Personalized and heterogeneous FL
Personalized Federated Learning under Local Supervision
Qiqi Liu, Jiaqiang Li, Yuchen Liu, Yaochu Jin, Lingjuan Lyu, Xiaohu Wu, Han Yu
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 |
|---|---|---|---|
| let clients use heterogeneous supervisor architectures (Transformer, CNN, LeNet-5) (ablation) | FedSimSup · CIFAR10 (Dirichlet 0.1, 100 clients) | accuracy: .892 -> .861 | Hurt |
| let clients use heterogeneous supervisors (ablation) | FedSimSup · CIFAR100 (Dirichlet 0.1, 100 clients) | accuracy: .503 -> .460 | Hurt |
| use pre-trained Transformer supervisor on a client (ablation) | FedSimSup · CIFAR10 (Dirichlet 0.1, 100 clients) | accuracy: .892 -> .898 | Improved |
| use CNN supervisor instead of LeNet-5 supervisor (ablation) | FedSimSup-TCL · CIFAR10 (Dirichlet 0.1, 100 clients) | accuracy: .851 -> .835 | Hurt |
| add similarity information for model aggregation (ablation) | FedSimSup · CIFAR10 (Dirichlet 0.1) | convergence speed | Improved |
| use parallel supervisor architecture instead of serial FedRep-style architecture (ablation) | FedSimSup · CIFAR100 (Dirichlet 0.1) | accuracy | Improved |
| increase C and gamma to (40, 3/7) from smaller pairs (ablation) | FedSimSup · CIFAR10 and CIFAR100 | accuracy | Improved |
| add FedSimSup supervisor and similarity aggregation versus FedAs | FedAs · CIFAR100 (Dirichlet 0.1, 100 clients) | accuracy: .467 -> .503 | Improved |
| add FedSimSup versus local training on Pathological split | Local · CIFAR100 (Pathological, 100 clients, 20 shards) | accuracy: .275 -> .464 | Improved |
| apply FedSimSup under Pathological split with 5 shards | pFedFda · CIFAR100 (Pathological, 100 clients, 5 shards) | accuracy: .642 -> .637 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FedAs — FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024) · better on 8 of 8 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
- FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024 · similarity 0.92)
- Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees (ICML 2025 · similarity 0.91)
- Adaptive Latent-Space Constraints in Personalized Federated Learning (NeurIPS 2025 · similarity 0.90)
- PFedCS: A Personalized Federated Learning Method for Enhancing Collaboration among Similar Classifiers (AAAI 2025 · similarity 0.90)
- PeFLL: Personalized Federated Learning by Learning to Learn (ICLR 2024 · similarity 0.90)
- Flexible Sharpness-Aware Personalized Federated Learning (AAAI 2025 · similarity 0.90)
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.
