Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedHPro: Federated Hyper-Prototype Learning via Gradient Matching
Huan Wang, Jun Shen, Haoran Li, Zhenyu Yang, Jun Yan, Ousman Manjang, Yanlong Zhai, Di Wu, Guansong Pang
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 HPCL (hyper-prototype contrastive learning) to FedAvg (ablation) | FedAvg · Digits | avg accuracy: 78.82 -> 83.58 | Improved |
| add HPAL (hyper-prototype alignment learning) to FedAvg (ablation) | FedAvg · Digits | avg accuracy: 78.82 -> 83.94 | Improved |
| combine HPCL and HPAL (ablation) | FedHPro · Digits | avg accuracy: 83.94 -> 84.80 | Improved |
| combine HPCL and HPAL (ablation) | FedHPro · Office-Caltech | avg accuracy: 61.34 -> 64.52 | Improved |
| replace hyper-prototypes with FedAvg-style global prototypes P in both HPCL and HPAL (ablation) | FedHPro · Digits | avg accuracy: 84.80 -> 81.35 | Hurt |
| replace hyper-prototypes with global prototypes P in both modules (ablation) | FedHPro · Office-Caltech | avg accuracy: 64.52 -> 59.69 | Hurt |
| replace hyper-prototypes with global prototypes P in both modules (ablation) | FedHPro · CIFAR10-LT | accuracy: 74.69 -> 72.56 | Hurt |
| replace global prototypes with hyper-prototypes in FedProto | FedProto · Digits | avg accuracy: 80.41 -> 81.75 | Improved |
| plug hyper-prototypes into FedTGP, FedGMKD and FedSA | FedTGP, FedGMKD, FedSA · Digits | avg accuracy: FedTGP 82.61, FedGMKD 82.79, FedSA 83.25 (+0.94, +0.96, +0.71) | Improved |
| add client-specific margin d_k in HPCL (ablation) | FedHPro · CIFAR10 NID10.5, CIFAR10-LT, Digits, Office-Caltech | accuracy: Digits 84.22 -> 84.80; Office-Caltech 63.90 -> 64.52; CIFAR10 88.83 -> 89.56 | Improved |
| increase hyper-prototype rounds M up to 30 (ablation) | FedHPro · Digits and CIFAR10-LT | accuracy: gain marginal beyond M=30 | Improved |
| excessively increase hyper-prototype length |I| (ablation) | FedHPro · Digits and CIFAR10-LT | accuracy | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FedSA — FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning (AAAI 2025) · better on 7 of 7 shared results
- FedGMKD — FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Discrepancy-Aware Aggregation (NeurIPS 2024) · better on 2 of 2 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
- FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning (AAAI 2025 · similarity 0.91)
- Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains (NeurIPS 2024 · similarity 0.90)
- Beyond Federated Prototype Learning: Learnable Semantic Anchors with Hyperspherical Contrast for Domain-Skewed Data (AAAI 2025 · similarity 0.90)
- FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning (AAAI 2024 · similarity 0.87)
- Federated Graph Learning under Domain Shift with Generalizable Prototypes (AAAI 2024 · similarity 0.87)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.86)
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.
