Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.06599 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914916200349696 |
|---|---|
| author | Ghannou, Omar Bennani, Younès |
| author_facet | Ghannou, Omar Bennani, Younès |
| contents | Multi-source Domain Adaptation (MDA) seeks to adapt models trained on data from multiple labeled source domains to perform effectively on an unlabeled target domain data, assuming access to sources data. To address the challenges of model adaptation and data privacy, we introduce Collaborative MDA Through Optimal Transport (CMDA-OT), a novel framework consisting of two key phases. In the first phase, each source domain is independently adapted to the target domain using optimal transport methods. In the second phase, a centralized collaborative learning architecture is employed, which aggregates the N models from the N sources without accessing their data, thereby safeguarding privacy. During this process, the server leverages a small set of pseudo-labeled samples from the target domain, known as the target validation subset, to refine and guide the adaptation. This dual-phase approach not only improves model performance on the target domain but also addresses vital privacy challenges inherent in domain adaptation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_06599 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Collaborative Multi-source Domain Adaptation Through Optimal Transport Ghannou, Omar Bennani, Younès Machine Learning Artificial Intelligence Multi-source Domain Adaptation (MDA) seeks to adapt models trained on data from multiple labeled source domains to perform effectively on an unlabeled target domain data, assuming access to sources data. To address the challenges of model adaptation and data privacy, we introduce Collaborative MDA Through Optimal Transport (CMDA-OT), a novel framework consisting of two key phases. In the first phase, each source domain is independently adapted to the target domain using optimal transport methods. In the second phase, a centralized collaborative learning architecture is employed, which aggregates the N models from the N sources without accessing their data, thereby safeguarding privacy. During this process, the server leverages a small set of pseudo-labeled samples from the target domain, known as the target validation subset, to refine and guide the adaptation. This dual-phase approach not only improves model performance on the target domain but also addresses vital privacy challenges inherent in domain adaptation. |
| title | Collaborative Multi-source Domain Adaptation Through Optimal Transport |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2404.06599 |