Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains
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_ | 1866908381344694272 |
|---|---|
| author | Ahmed, Sabbir Rizve, Mamshad Nayeem Arafat, Abdullah Al Liu, Jacqueline Hossain, Rahim Nahian, Mohaiminul Al Rakin, Adnan Siraj |
| author_facet | Ahmed, Sabbir Rizve, Mamshad Nayeem Arafat, Abdullah Al Liu, Jacqueline Hossain, Rahim Nahian, Mohaiminul Al Rakin, Adnan Siraj |
| contents | Semi-Supervised Federated Learning (SSFL) is gaining popularity over conventional Federated Learning in many real-world applications. Due to the practical limitation of limited labeled data on the client side, SSFL considers that participating clients train with unlabeled data, and only the central server has the necessary resources to access limited labeled data, making it an ideal fit for real-world applications (e.g., healthcare). However, traditional SSFL assumes that the data distributions in the training phase and testing phase are the same. In practice, however, domain shifts frequently occur, making it essential for SSFL to incorporate generalization capabilities and enhance their practicality. The core challenge is improving model generalization to new, unseen domains while the client participate in SSFL. However, the decentralized setup of SSFL and unsupervised client training necessitates innovation to achieve improved generalization across domains. To achieve this, we propose a novel framework called the Unified Alignment Protocol (UAP), which consists of an alternating two-stage training process. The first stage involves training the server model to learn and align the features with a parametric distribution, which is subsequently communicated to clients without additional communication overhead. The second stage proposes a novel training algorithm that utilizes the server feature distribution to align client features accordingly. Our extensive experiments on standard domain generalization benchmark datasets across multiple model architectures reveal that proposed UAP successfully achieves SOTA generalization performance in SSFL setting. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_21010 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains Ahmed, Sabbir Rizve, Mamshad Nayeem Arafat, Abdullah Al Liu, Jacqueline Hossain, Rahim Nahian, Mohaiminul Al Rakin, Adnan Siraj Computer Vision and Pattern Recognition Machine Learning Semi-Supervised Federated Learning (SSFL) is gaining popularity over conventional Federated Learning in many real-world applications. Due to the practical limitation of limited labeled data on the client side, SSFL considers that participating clients train with unlabeled data, and only the central server has the necessary resources to access limited labeled data, making it an ideal fit for real-world applications (e.g., healthcare). However, traditional SSFL assumes that the data distributions in the training phase and testing phase are the same. In practice, however, domain shifts frequently occur, making it essential for SSFL to incorporate generalization capabilities and enhance their practicality. The core challenge is improving model generalization to new, unseen domains while the client participate in SSFL. However, the decentralized setup of SSFL and unsupervised client training necessitates innovation to achieve improved generalization across domains. To achieve this, we propose a novel framework called the Unified Alignment Protocol (UAP), which consists of an alternating two-stage training process. The first stage involves training the server model to learn and align the features with a parametric distribution, which is subsequently communicated to clients without additional communication overhead. The second stage proposes a novel training algorithm that utilizes the server feature distribution to align client features accordingly. Our extensive experiments on standard domain generalization benchmark datasets across multiple model architectures reveal that proposed UAP successfully achieves SOTA generalization performance in SSFL setting. |
| title | Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2505.21010 |