Research map / Federated learning and privacy / Personalized and heterogeneous FL
Personalized Federated Domain-Incremental Learning based on Adaptive Knowledge Matching
Yichen Li, Wenchao Xu, Haozhao Wang, Yining Qi, Jingcai Guo, Ruixuan Li
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 migration loss (ablation) | pFedDIL · Digit-10 | average accuracy (%): 86.45 -> 89.28 | Improved |
| add knowledge migration loss (ablation) | pFedDIL · DomainNet | average accuracy (%): 48.79 -> 51.69 | Improved |
| add correlation-weighted ensemble inference (ablation) | pFedDIL · Digit-10 | average accuracy (%): 87.73 -> 89.28 | Improved |
| add partial parameter sharing between auxiliary classifier and model (ablation) | pFedDIL · Digit-10 | average accuracy (%): 89.18 -> 89.28 | No clear effect |
| add partial parameter sharing (ablation) | pFedDIL · Office-31 | average accuracy (%): 45.52 -> 46.17 | No clear effect |
| use pFedDIL versus FedCIL | federated domain-incremental learning · DomainNet | average accuracy (%): 47.64 -> 51.69 | Improved |
| use pFedDIL versus FedAvg in communication cost | federated learning · Digit-10 | rounds to best performance: 480 -> 379 | Improved |
| use pFedDIL versus FedAvg in time per round | federated learning · Digit-10 | seconds per round: 32.14 -> 34.91 | Hurt |
| raise lambda from 0.0 to 1.0 (more personalized models) (ablation) | pFedDIL · Digit-10 | average accuracy (%) / model size: 82.43 -> 93.94; 22Mb -> 88Mb | Mixed |
| use disjoint per-domain models (upper bound) versus pFedDIL | pFedDIL · DomainNet | average accuracy (%): 51.69 -> 53.26 | Improved |
Closest papers by meaning
- pFedMxF: Personalized Federated Class-Incremental Learning with Mixture of Frequency Aggregation (CVPR 2025 · similarity 0.86)
- PeFLL: Personalized Federated Learning by Learning to Learn (ICLR 2024 · similarity 0.85)
- FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024 · similarity 0.85)
- Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation (NeurIPS 2025 · similarity 0.85)
- PFedCS: A Personalized Federated Learning Method for Enhancing Collaboration among Similar Classifiers (AAAI 2025 · similarity 0.85)
- FedPHA: Federated Prompt Learning for Heterogeneous Client Adaptation (ICML 2025 · similarity 0.85)
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.
