mlsanityData to 14 Oct 2026

FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion

arXiv 2603.29455 ↗First posted 31 Mar 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated prototype learning (FPL), as a solution to heterogeneous federated learning (HFL), effectively alleviates the challenges of data and model heterogeneity.However, existing FPL methods fail to balance the fidelity and discriminability of the feature, and are limited by a single global prototype. In this paper, we propose FedDBP, a novel FPL method to address the above issues. On the client-side, we design a Dual-Branch feature projector that employs L2 alignment and contrastive learning simultaneously, thereby ensuring both the fidelity and discriminability of local features. On the server-side, we introduce a Personalized global prototype fusion approach that leverages Fisher information to identify the important channels of local prototypes. Extensive experiments demonstrate the superiority of FedDBP over ten existing advanced methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 31 Mar 2026.

Builds on

19 of 27 references.

References · 19

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  3. 2018Federated Learning with Non-IID Datacited by 1,108
  4. 2021Model-Contrastive Federated Learningcited by 766
  5. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  6. 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
  7. 2017A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetscited by 377
  8. 2020Adaptive Personalized Federated Learningcited by 358
  9. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 352
  10. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 337
  11. 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
  12. 2018Communication-Efficient On-Device Machine Learning: Federated Distillation and Augmentation under Non-IID Private Datacited by 243
7 more
  1. 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
  2. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 161
  3. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 81
  4. 2024FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learningcited by 47
  5. 2024Federated Model Heterogeneous Matryoshka Representation Learningcited by 21
  6. 2024An Upload-Efficient Scheme for Transferring Knowledge From a Server-Side Pre-trained Generator to Clients in Heterogeneous Federated Learningcited by 17
  7. 2025HtFLlib: A Comprehensive Heterogeneous Federated Learning Library and Benchmarkcited by 7

Built on by

Not cited yet.