mlsanityData to 7 Oct 2026

FedHPro: Federated Hyper-Prototype Learning via Gradient Matching

arXiv 2605.13475 ↗First posted 13 May 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) enables collaborative training of distributed clients while protecting privacy. To enhance generalization capability in FL, prototype-based FL is in the spotlight, since shared global prototypes offer semantic anchors for aligning client-specific local prototypes. However, existing methods update global prototypes at the prototype-level via averaging local prototypes or refining global anchors, which often leads to semantic drift across clients and subsequently yields a misaligned global signal. To alleviate this issue, we introduce hyper-prototypes, defined by a set of learnable global class-wise prototypes to preserve underlying semantic knowledge across clients. The hyper-prototypes are optimized via gradient matching to align with class-relevant characteristics distilled directly from clients' real samples, rather than prototype-level descriptors. We further propose FedHPro, a Federated Hyper-Prototype Learning framework, to leverage hyper-prototypes to promote inter-class separability via mutual-contrastive learning with client-specific margin, while encouraging intra-class uniformity through a consistency penalty. Comprehensive experiments under diverse heterogeneous scenarios confirm that 1) hyper-prototypes produce a more semantically consistent global signal, and 2) FedHPro achieves state-of-the-art performance on several benchmark datasets. Code is available at hrefhttps://github.com/mala-lab/FedHProhttps://github.com/mala-lab/FedHPro.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 47 of its 66 references that are in the map. First posted on arXiv 13 May 2026.

Builds on

47 of 66 references.

References · 47

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  5. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  6. 2014Going Deeper with Convolutionscited by 4,231
  7. 2019Advances and Open Problems in Federated Learningcited by 3,021
  8. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  9. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  10. 2018Moment Matching for Multi-Source Domain Adaptationcited by 1,327
  11. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  12. 2020Graph Contrastive Learning with Augmentationscited by 1,203
35 more
  1. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 987
  2. 2020What Makes for Good Views for Contrastive Learning?cited by 843
  3. 2021Model-Contrastive Federated Learningcited by 762
  4. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
  5. 2020Federated Learning with Matched Averagingcited by 564
  6. 2019Fair Resource Allocation in Federated Learningcited by 389
  7. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  8. 2021Federated Learning on Non-IID Data: A Surveycited by 345
  9. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  10. 2023A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trendscited by 205
  11. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  12. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 141
  13. 2022Rethinking Semantic Segmentation: A Prototype Viewcited by 140
  14. 2018Robust Classification with Convolutional Prototype Learningcited by 122
  15. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  16. 2021Contrastive Learning with Stronger Augmentationscited by 100
  17. 2023Stochastic Controlled Averaging for Federated Learning with Communication Compressioncited by 100
  18. 2015A Sensitivity Analysis of (and Practitioners' Guide to) Convolutional Neural Networks for Sentence Classificationcited by 92
  19. 2022Tackling Data Heterogeneity in Federated Learning with Class Prototypescited by 66
  20. 2023FedDisco: Federated Learning with Discrepancy-Aware Collaborationcited by 66
  21. 2022FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Datacited by 49
  22. 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
  23. 2023Panoptic Scene Graph Generation with Semantics-Prototype Learningcited by 42
  24. 2023Learning Support and Trivial Prototypes for Interpretable Image Classificationcited by 38
  25. 2024Relaxed Contrastive Learning for Federated Learningcited by 32
  26. 2023Contrastive Feature Masking Open-Vocabulary Vision Transformercited by 31
  27. 2022Online Continual Learning with Contrastive Vision Transformercited by 21
  28. 2023A Simple Data Augmentation for Feature Distribution Skewed Federated Learningcited by 16
  29. 2025Geometric Knowledge-Guided Localized Global Distribution Alignment for Federated Learningcited by 11
  30. 2025FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learningcited by 8
  31. 2024Contrastive Learning with Synthetic Positivescited by 6
  32. 2025Federated Learning with Sample-level Client Drift Mitigationcited by 6
  33. 2024PRAGA: Prototype-aware Graph Adaptive Aggregation for Spatial Multi-modal Omics Analysiscited by 5
  34. 2023Feature Selection in the Contrastive Analysis Settingcited by 3
  35. 2025FedSC: Federated Learning with Semantic-Aware Collaborationcited by 3

Built on by

Not cited yet.