Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.05955 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918491722874880 |
|---|---|
| author | Chen, Yuliang Lin, Xi Wu, Jun Cai, Xiangrui Zhang, Qiaolun Fan, Xichun Xu, Jiapeng Su, Xiu |
| author_facet | Chen, Yuliang Lin, Xi Wu, Jun Cai, Xiangrui Zhang, Qiaolun Fan, Xichun Xu, Jiapeng Su, Xiu |
| contents | Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity and incur significant communication and computation overhead. To address these challenges, this paper presents a new FDG framework, dubbed FaST-PT, which facilitates local feature augmentation and efficient unseen domain adaptation in a distributed manner. First, we propose a lightweight Multi-Modal Style Transfer (MST) method to transform image embedding under text supervision, which could expand the training data distribution and mitigate domain shift. We then design a dual-prompt module that decomposes the prompt into global and domain prompts. Specifically, global prompts capture general knowledge from augmented embedding across clients, while domain prompts capture domain-specific knowledge from local data. Besides, Domain-aware Prompt Generation (DPG) is introduced to adaptively generate suitable prompts for each sample, which facilitates unseen domain adaptation through knowledge fusion. Extensive experiments on four cross-domain benchmark datasets, e.g., PACS and DomainNet, demonstrate the superior performance of FaST-PT over SOTA FDG methods such as FedDG-GA and DiPrompt. Ablation studies further validate the effectiveness and efficiency of FaST-PT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_05955 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Multi-Modal Style Transfer-based Prompt Tuning for Efficient Federated Domain Generalization Chen, Yuliang Lin, Xi Wu, Jun Cai, Xiangrui Zhang, Qiaolun Fan, Xichun Xu, Jiapeng Su, Xiu Distributed, Parallel, and Cluster Computing Federated Domain Generalization (FDG) aims to collaboratively train a global model across distributed clients that can generalize well on unseen domains. However, existing FDG methods typically struggle with cross-client data heterogeneity and incur significant communication and computation overhead. To address these challenges, this paper presents a new FDG framework, dubbed FaST-PT, which facilitates local feature augmentation and efficient unseen domain adaptation in a distributed manner. First, we propose a lightweight Multi-Modal Style Transfer (MST) method to transform image embedding under text supervision, which could expand the training data distribution and mitigate domain shift. We then design a dual-prompt module that decomposes the prompt into global and domain prompts. Specifically, global prompts capture general knowledge from augmented embedding across clients, while domain prompts capture domain-specific knowledge from local data. Besides, Domain-aware Prompt Generation (DPG) is introduced to adaptively generate suitable prompts for each sample, which facilitates unseen domain adaptation through knowledge fusion. Extensive experiments on four cross-domain benchmark datasets, e.g., PACS and DomainNet, demonstrate the superior performance of FaST-PT over SOTA FDG methods such as FedDG-GA and DiPrompt. Ablation studies further validate the effectiveness and efficiency of FaST-PT. |
| title | Multi-Modal Style Transfer-based Prompt Tuning for Efficient Federated Domain Generalization |
| topic | Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2601.05955 |