Dual-Distilled Heterogeneous Federated Learning with Adaptive Margins for Trainable Global Prototypes
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908720943857664 |
|---|---|
| author | Siddika, Fatema Hossen, Md Anwar Zhang, Wensheng Sharma, Anuj Muñoz, Juan Pablo Jannesari, Ali |
| author_facet | Siddika, Fatema Hossen, Md Anwar Zhang, Wensheng Sharma, Anuj Muñoz, Juan Pablo Jannesari, Ali |
| contents | Heterogeneous Federated Learning (HFL) has gained significant attention for its capacity to handle both model and data heterogeneity across clients. Prototype-based HFL methods emerge as a promising solution to address statistical and model heterogeneity as well as privacy challenges, paving the way for new advancements in HFL research. This method focuses on sharing class-representative prototypes among heterogeneous clients. However, aggregating these prototypes via standard weighted averaging often yields sub-optimal global knowledge. Specifically, the averaging approach induces a shrinking of the aggregated prototypes' decision margins, thereby degrading model performance in scenarios with model heterogeneity and non-IID data distributions. The propose FedProtoKD in a Heterogeneous Federated Learning setting, utilizing an enhanced dual-knowledge distillation mechanism to enhance system performance by leveraging clients' logits and prototype feature representations. The proposed framework aims to resolve the prototype margin-shrinking problem using a contrastive learning-based trainable server prototype by leveraging a class-wise adaptive prototype margin. Furthermore, the framework assess the importance of public samples using the closeness of the sample's prototype to its class representative prototypes, which enhances learning performance. FedProtoKD improved test accuracy by an average of 1.13% and up to 34.13% across various settings, significantly outperforming existing state-of-the-art HFL methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19009 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dual-Distilled Heterogeneous Federated Learning with Adaptive Margins for Trainable Global Prototypes Siddika, Fatema Hossen, Md Anwar Zhang, Wensheng Sharma, Anuj Muñoz, Juan Pablo Jannesari, Ali Machine Learning Distributed, Parallel, and Cluster Computing Heterogeneous Federated Learning (HFL) has gained significant attention for its capacity to handle both model and data heterogeneity across clients. Prototype-based HFL methods emerge as a promising solution to address statistical and model heterogeneity as well as privacy challenges, paving the way for new advancements in HFL research. This method focuses on sharing class-representative prototypes among heterogeneous clients. However, aggregating these prototypes via standard weighted averaging often yields sub-optimal global knowledge. Specifically, the averaging approach induces a shrinking of the aggregated prototypes' decision margins, thereby degrading model performance in scenarios with model heterogeneity and non-IID data distributions. The propose FedProtoKD in a Heterogeneous Federated Learning setting, utilizing an enhanced dual-knowledge distillation mechanism to enhance system performance by leveraging clients' logits and prototype feature representations. The proposed framework aims to resolve the prototype margin-shrinking problem using a contrastive learning-based trainable server prototype by leveraging a class-wise adaptive prototype margin. Furthermore, the framework assess the importance of public samples using the closeness of the sample's prototype to its class representative prototypes, which enhances learning performance. FedProtoKD improved test accuracy by an average of 1.13% and up to 34.13% across various settings, significantly outperforming existing state-of-the-art HFL methods. |
| title | Dual-Distilled Heterogeneous Federated Learning with Adaptive Margins for Trainable Global Prototypes |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2508.19009 |