Research map / Federated learning and privacy / Personalized and heterogeneous FL
Intra-Class Unbiased Prototype Aggregation and Classifier Collaboration for Personalized Federated Learning
Hao Zheng, Shiyu Song, Zhigang Hu, Meiguang Zheng, Liu Yang, Aikun Xu, Rongchang Zhao, Ruizhi Pu, Ruiyi Fang, Boyu Wang
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 |
|---|---|---|---|
| intra-class prototype clustering and classifier collaboration instead of FedCCFA | FedIC · CIFAR100 pathological | accuracy: 67.93 -> 75.50 | Improved |
| FedIC vs FedCCFA | FedIC · CIFAR100 practical | accuracy: 56.72 -> 65.89 | Improved |
| FedIC vs FedCCFA | FedIC · FMNIST pathological | accuracy: 99.20 -> 99.42 | No clear effect |
| FedIC vs best baseline with ResNet18 backbone | FedIC · CIFAR10 practical (ResNet18) | accuracy: 92.89 -> 92.83 | Hurt |
| deeper backbone (ResNet10) vs shallow CNN | FedIC · CIFAR100 practical | accuracy: 65.89 -> 72.54 | Improved |
| increase clients from 40 to 60 | FedIC · CIFAR100 practical | accuracy: 65.89 -> 65.36 | No clear effect |
| lower Dirichlet beta from 0.5 to 0.01 | FedIC · CIFAR100 practical | accuracy: 71.43 -> 59.82 | Hurt |
| lower Dirichlet beta from 0.5 to 0.01 | baselines · CIFAR100 practical | accuracy: 62.85 -> 48.03 (FedCCFA) | Hurt |
| add intra-class prototype clustering to global prototype aggregation (ablation) | FedIC · CIFAR100 | accuracy | Improved |
| add classifier collaboration alone (ablation) | FedIC · CIFAR100 | accuracy | Improved |
| combine clustering and classifier collaboration (ablation) | FedIC · CIFAR100 | accuracy | Improved |
| use more clusters than optimal (ablation) | FedIC · FMNIST, CIFAR10, CIFAR100 | accuracy | Hurt |
Closest papers by meaning
- Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains (NeurIPS 2024 · similarity 0.91)
- PFedCS: A Personalized Federated Learning Method for Enhancing Collaboration among Similar Classifiers (AAAI 2025 · similarity 0.89)
- FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning (AAAI 2025 · similarity 0.88)
- Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation (NeurIPS 2025 · similarity 0.87)
- pFedMxF: Personalized Federated Class-Incremental Learning with Mixture of Frequency Aggregation (CVPR 2025 · similarity 0.87)
- FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation (NeurIPS 2024 · similarity 0.87)
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.
