On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913975083466752 |
|---|---|
| author | Bai, Jiahui Dong, Hai Qin, A. K. |
| author_facet | Bai, Jiahui Dong, Hai Qin, A. K. |
| contents | Decentralized Federated Learning (DFL) struggles with the slow adaptation of late-joining delayed clients and high communication costs in asynchronous environments. These limitations significantly hinder overall performance. To address this, we propose DFedCAD, a novel framework for rapid adaptation via Centroid-Aligned Distillation. DFedCAD first employs Weighted Cluster Pruning (WCP) to compress models into representative centroids, drastically reducing communication overhead. It then enables delayed clients to intelligently weigh and align with peer knowledge using a novel structural distance metric and a differentiable k-means distillation module, facilitating efficient end-to-end knowledge transfer. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet show that DFedCAD consistently achieves state-of-the-art performance, attaining the highest accuracy across all evaluated settings while reducing communication overhead by over 86%. Our framework provides a scalable and practical solution for efficient decentralized learning in dynamic, real-world scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_02993 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach Bai, Jiahui Dong, Hai Qin, A. K. Machine Learning Decentralized Federated Learning (DFL) struggles with the slow adaptation of late-joining delayed clients and high communication costs in asynchronous environments. These limitations significantly hinder overall performance. To address this, we propose DFedCAD, a novel framework for rapid adaptation via Centroid-Aligned Distillation. DFedCAD first employs Weighted Cluster Pruning (WCP) to compress models into representative centroids, drastically reducing communication overhead. It then enables delayed clients to intelligently weigh and align with peer knowledge using a novel structural distance metric and a differentiable k-means distillation module, facilitating efficient end-to-end knowledge transfer. Extensive experiments on CIFAR-10, CIFAR-100, and Tiny-ImageNet show that DFedCAD consistently achieves state-of-the-art performance, attaining the highest accuracy across all evaluated settings while reducing communication overhead by over 86%. Our framework provides a scalable and practical solution for efficient decentralized learning in dynamic, real-world scenarios. |
| title | On the Fast Adaptation of Delayed Clients in Decentralized Federated Learning: A Centroid-Aligned Distillation Approach |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.02993 |