FLIP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning
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_ | 1866909556000423936 |
|---|---|
| author | Liao, Dongping Gao, Xitong Xu, Yabo Xu, Chengzhong |
| author_facet | Liao, Dongping Gao, Xitong Xu, Yabo Xu, Chengzhong |
| contents | The increasing emphasis on privacy and data security has driven the adoption of federated learning, a decentralized approach to train machine learning models without sharing raw data. Prompt learning, which fine-tunes prompt embeddings of pretrained models, offers significant advantages in federated settings by reducing computational costs and communication overheads while leveraging the strong performance and generalization capabilities of vision-language models such as CLIP. This paper addresses the intersection of federated learning and prompt learning, particularly for vision-language models. In this work, we introduce a comprehensive framework, named FLIP, to evaluate federated prompt learning algorithms. FLIP assesses the performance of 8 state-of-the-art federated prompt learning methods across 4 federated learning protocols and 12 open datasets, considering 6 distinct evaluation scenarios. Our findings demonstrate that prompt learning maintains strong generalization performance in both in-distribution and out-of-distribution settings with minimal resource consumption. This work highlights the effectiveness of federated prompt learning in environments characterized by data scarcity, unseen classes, and cross-domain distributional shifts. We open-source the code for all implemented algorithms in FLIP to facilitate further research in this domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_22263 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FLIP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning Liao, Dongping Gao, Xitong Xu, Yabo Xu, Chengzhong Machine Learning Computer Vision and Pattern Recognition The increasing emphasis on privacy and data security has driven the adoption of federated learning, a decentralized approach to train machine learning models without sharing raw data. Prompt learning, which fine-tunes prompt embeddings of pretrained models, offers significant advantages in federated settings by reducing computational costs and communication overheads while leveraging the strong performance and generalization capabilities of vision-language models such as CLIP. This paper addresses the intersection of federated learning and prompt learning, particularly for vision-language models. In this work, we introduce a comprehensive framework, named FLIP, to evaluate federated prompt learning algorithms. FLIP assesses the performance of 8 state-of-the-art federated prompt learning methods across 4 federated learning protocols and 12 open datasets, considering 6 distinct evaluation scenarios. Our findings demonstrate that prompt learning maintains strong generalization performance in both in-distribution and out-of-distribution settings with minimal resource consumption. This work highlights the effectiveness of federated prompt learning in environments characterized by data scarcity, unseen classes, and cross-domain distributional shifts. We open-source the code for all implemented algorithms in FLIP to facilitate further research in this domain. |
| title | FLIP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning |
| topic | Machine Learning Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.22263 |