FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation
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_ | 1866918236023422976 |
|---|---|
| author | Yashwanth, M Koti, Sampath Singh, Arunabh Marjit, Shyam Chakraborty, Anirban |
| author_facet | Yashwanth, M Koti, Sampath Singh, Arunabh Marjit, Shyam Chakraborty, Anirban |
| contents | We address the Federated source-Free Domain Adaptation (FFreeDA) problem, with clients holding unlabeled data with significant inter-client domain gaps. The FFreeDA setup constrains the FL frameworks to employ only a pre-trained server model as the setup restricts access to the source dataset during the training rounds. Often, this source domain dataset has a distinct distribution to the clients' domains. To address the challenges posed by the FFreeDA setup, adaptation of the Source-Free Domain Adaptation (SFDA) methods to FL struggles with client-drift in real-world scenarios due to extreme data heterogeneity caused by the aforementioned domain gaps, resulting in unreliable pseudo-labels. In this paper, we introduce FedSCAl, an FL framework leveraging our proposed Server-Client Alignment (SCAl) mechanism to regularize client updates by aligning the clients' and server model's predictions. We observe an improvement in the clients' pseudo-labeling accuracy post alignment, as the SCAl mechanism helps to mitigate the client-drift. Further, we present extensive experiments on benchmark vision datasets showcasing how FedSCAl consistently outperforms state-of-the-art FL methods in the FFreeDA setup for classification tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_06738 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation Yashwanth, M Koti, Sampath Singh, Arunabh Marjit, Shyam Chakraborty, Anirban Computer Vision and Pattern Recognition We address the Federated source-Free Domain Adaptation (FFreeDA) problem, with clients holding unlabeled data with significant inter-client domain gaps. The FFreeDA setup constrains the FL frameworks to employ only a pre-trained server model as the setup restricts access to the source dataset during the training rounds. Often, this source domain dataset has a distinct distribution to the clients' domains. To address the challenges posed by the FFreeDA setup, adaptation of the Source-Free Domain Adaptation (SFDA) methods to FL struggles with client-drift in real-world scenarios due to extreme data heterogeneity caused by the aforementioned domain gaps, resulting in unreliable pseudo-labels. In this paper, we introduce FedSCAl, an FL framework leveraging our proposed Server-Client Alignment (SCAl) mechanism to regularize client updates by aligning the clients' and server model's predictions. We observe an improvement in the clients' pseudo-labeling accuracy post alignment, as the SCAl mechanism helps to mitigate the client-drift. Further, we present extensive experiments on benchmark vision datasets showcasing how FedSCAl consistently outperforms state-of-the-art FL methods in the FFreeDA setup for classification tasks. |
| title | FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.06738 |