Research map / Federated learning and privacy / Personalized and heterogeneous FL
Controlled Collaboration Geometry for Personalized Federated Learning
Hongbo Yin, Jichun Wu, Zhou Yang, Chi Jiang, Yin Zhang, Yan Zhang
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 |
|---|---|---|---|
| replace similarity-feedback dynamic weight updates with a fixed feedback-free affinity template (ablation) | pFedCCG · CIFAR-10 (beta=0.2) | personalized accuracy (%): 82.64 -> 85.20 | Improved |
| add the feedback-free template over SF (ablation) | pFedCCG · Yahoo (beta=0.2) | personalized accuracy (%): 77.81 -> 79.76 | Improved |
| add collaboration geometry scheduling (strong early mixing, weaker later) (ablation) | pFedCCG · CIFAR-10 (beta=0.2) | personalized accuracy (%): 84.72 -> 85.20 | Improved |
| add geometry scheduling (ablation) | pFedCCG · Aya LLM-SFT (k=3) | perplexity: 6.39 -> 6.35 | Improved |
| prescribe stationary distribution q equal to dataset proportions in the projection (ablation) | pFedCCG · CIFAR-10 (beta=0.2) | personalized accuracy (%): 85.01 -> 85.20 | Improved |
| add the q-stationary projection (ablation) | pFedCCG · Yahoo (beta=0.2) | personalized accuracy (%): 79.27 -> 79.76 | Improved |
| build affinity template from cosine similarity of initial model updates instead of JS divergence of data distributions (ablation) | pFedCCG · CIFAR-10 (beta=0.2) and MovieLens | accuracy / Recall@20: CIFAR-10 85.20 -> 85.22; RecSys 88.81 -> 88.56 | No clear effect |
| use weaker output-based proxy templates (softmax on 256 public samples) (ablation) | pFedCCG · CIFAR-10 (beta=1) | mean personalized accuracy (%): 78.35 -> 77.49 (softmax-cos); best baseline 76.27 | Hurt |
| use any proxy template instead of the JS template (ablation) | pFedCCG · CIFAR-10 (beta=0.2, 0.5, 1) | mean personalized accuracy (%): all proxies still above best baseline, e.g. 84.59 vs 83.97 at beta=0.2 | Mixed |
| use pFedCCG projection instead of adaptive graph learning for collaboration weights | collaboration overhead · 50 clients | extra seconds: pFedGraph 281.60 -> pFedCCG 0.04 | Improved |
| pFedCCG vs best baseline on Aya LoRA SFT | personalized LLM fine-tuning · Aya (k=3) Acc@5 | Acc@5 (%): 80.04 -> 80.12 | No clear effect |
| use clustering-style PFL (CFL, pFedCS) versus FedAvg-FT | personalized FL baselines · CIFAR-10 (beta=1) | personalized accuracy (%): FedAvg-FT 76.20 vs CFL 68.07, pFedCS 72.03 | Hurt |
Closest papers by meaning
- Decentralized Directed Collaboration for Personalized Federated Learning (CVPR 2024 · similarity 0.90)
- pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning (NeurIPS 2024 · similarity 0.89)
- PFedCS: A Personalized Federated Learning Method for Enhancing Collaboration among Similar Classifiers (AAAI 2025 · similarity 0.89)
- FedAS: Bridging Inconsistency in Personalized Federated Learning (CVPR 2024 · similarity 0.88)
- Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees (ICML 2025 · similarity 0.88)
- FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference (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.
