Research map / Federated learning and privacy / Personalized and heterogeneous FL
Flow: Per-instance Personalized Federated Learning
Kunjal Panchal, Sunav Choudhary, Nisarg Parikh, Lijun Zhang, Hui Guan
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 |
|---|---|---|---|
| remove regularization term from policy update (ablation) | Flow · Stackoverflow | generalized accuracy: 24.16% -> 26.64% | Improved |
| remove regularization term from policy update (ablation) | Flow · Stackoverflow | personalized accuracy: 27.59% -> 29.49% | Improved |
| per-instance routing instead of both paths being global (PI-Flow) (ablation) | Flow · Stackoverflow | personalized accuracy: 26.31% -> 29.49% | Improved |
| per-instance and per-client Flow instead of per-client only (PC-Flow, FedAvgFT) (ablation) | Flow · Stackoverflow | personalized accuracy: 24.41% -> 29.49% | Improved |
| dynamic routing instead of fixed instance-agnostic policy q0 (ablation) | Flow · Stackoverflow | validation accuracy (personalized) | Improved |
| fixed policy q0 = 0.25 (only local route at inference) (ablation) | Flow · Stackoverflow | validation accuracy (personalized) | Hurt |
| soft decisions instead of hard decisions at inference (ablation) | Flow · Stackoverflow | personalized accuracy: 29.49% -> 29.57% | No clear effect |
| Flow instead of best baseline | Flow · Stackoverflow, Shakespeare, EMNIST, CIFAR10/100 | generalized accuracy: +1.11-3.46% | Improved |
| Flow instead of best baseline | Flow · Stackoverflow, Shakespeare, EMNIST, CIFAR10/100 | personalized accuracy: +1.33-4.58% | Improved |
| Flow instead of KNNPER (other per-instance method) | Flow · Stackoverflow, Shakespeare, CIFAR10 | personalized accuracy: +1.33-6.97% | Improved |
| Flow instead of PartialFed | Flow · CIFAR100 (0.1) | generalized accuracy: 34.79% -> 34.00% | Hurt |
| Flow instead of PartialFed | Flow · CIFAR100 (0.6) | personalized accuracy: 40.18% -> 40.08% | No clear effect |
Closest papers by meaning
- Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees (ICML 2025 · similarity 0.90)
- PerAda: Parameter-Efficient Federated Learning Personalization with Generalization Guarantees (CVPR 2024 · similarity 0.89)
- Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients (NeurIPS 2024 · similarity 0.89)
- FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024 · similarity 0.89)
- Personalized Federated Learning via Feature Distribution Adaptation (NeurIPS 2024 · similarity 0.89)
- PeFLL: Personalized Federated Learning by Learning to Learn (ICLR 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.
