FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914434073493504 |
|---|---|
| author | Gao, Ningzhi Huang, Siquan Shi, Leyu Gao, Ying |
| author_facet | Gao, Ningzhi Huang, Siquan Shi, Leyu Gao, Ying |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_29455 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion Gao, Ningzhi Huang, Siquan Shi, Leyu Gao, Ying Computer Vision and Pattern Recognition 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. |
| title | FedDBP: Enhancing Federated Prototype Learning with Dual-Branch Features and Personalized Global Fusion |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.29455 |