Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised 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_ | 1866929658072662016 |
|---|---|
| author | Wang, Zhongwei Wu, Tong Chen, Zhiyong Qian, Liang Xu, Yin Tao, Meixia |
| author_facet | Wang, Zhongwei Wu, Tong Chen, Zhiyong Qian, Liang Xu, Yin Tao, Meixia |
| contents | Federated semi-supervised learning (FSSL) is primarily challenged by two factors: the scarcity of labeled data across clients and the non-independent and identically distribution (non-IID) nature of data among clients. In this paper, we propose a novel approach, diffusion model-based data synthesis aided FSSL (DDSA-FSSL), which utilizes a diffusion model (DM) to generate synthetic data, bridging the gap between heterogeneous local data distributions and the global data distribution. In DDSA-FSSL, clients address the challenge of the scarcity of labeled data by employing a federated learning-trained classifier to perform pseudo labeling for unlabeled data. The DM is then collaboratively trained using both labeled and precision-optimized pseudo-labeled data, enabling clients to generate synthetic samples for classes that are absent in their labeled datasets. This process allows clients to generate more comprehensive synthetic datasets aligned with the global distribution. Extensive experiments conducted on multiple datasets and varying non-IID distributions demonstrate the effectiveness of DDSA-FSSL, e.g., it improves accuracy from 38.46% to 52.14% on CIFAR-10 datasets with 10% labeled data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_02219 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised Learning Wang, Zhongwei Wu, Tong Chen, Zhiyong Qian, Liang Xu, Yin Tao, Meixia Machine Learning Artificial Intelligence Information Theory Federated semi-supervised learning (FSSL) is primarily challenged by two factors: the scarcity of labeled data across clients and the non-independent and identically distribution (non-IID) nature of data among clients. In this paper, we propose a novel approach, diffusion model-based data synthesis aided FSSL (DDSA-FSSL), which utilizes a diffusion model (DM) to generate synthetic data, bridging the gap between heterogeneous local data distributions and the global data distribution. In DDSA-FSSL, clients address the challenge of the scarcity of labeled data by employing a federated learning-trained classifier to perform pseudo labeling for unlabeled data. The DM is then collaboratively trained using both labeled and precision-optimized pseudo-labeled data, enabling clients to generate synthetic samples for classes that are absent in their labeled datasets. This process allows clients to generate more comprehensive synthetic datasets aligned with the global distribution. Extensive experiments conducted on multiple datasets and varying non-IID distributions demonstrate the effectiveness of DDSA-FSSL, e.g., it improves accuracy from 38.46% to 52.14% on CIFAR-10 datasets with 10% labeled data. |
| title | Diffusion Model-Based Data Synthesis Aided Federated Semi-Supervised Learning |
| topic | Machine Learning Artificial Intelligence Information Theory |
| url | https://arxiv.org/abs/2501.02219 |