Rethinking the Flow-Based Gradual Domain Adaption: A Semi-Dual Optimal Transport Perspective
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917239543824384 |
|---|---|
| author | Chen, Zhichao Zhuang, Zhan Teng, Yunfei Wang, Hao Wang, Fangyikang Li, Zhengnan Liu, Tianqiao Li, Haoxuan Lin, Zhouchen |
| author_facet | Chen, Zhichao Zhuang, Zhan Teng, Yunfei Wang, Hao Wang, Fangyikang Li, Zhengnan Liu, Tianqiao Li, Haoxuan Lin, Zhouchen |
| contents | Gradual domain adaptation (GDA) aims to mitigate domain shift by progressively adapting models from the source domain to the target domain via intermediate domains. However, real intermediate domains are often unavailable or ineffective, necessitating the synthesis of intermediate samples. Flow-based models have recently been used for this purpose by interpolating between source and target distributions; however, their training typically relies on sample-based log-likelihood estimation, which can discard useful information and thus degrade GDA performance. The key to addressing this limitation is constructing the intermediate domains via samples directly. To this end, we propose an Entropy-regularized Semi-dual Unbalanced Optimal Transport (E-SUOT) framework to construct intermediate domains. Specifically, we reformulate flow-based GDA as a Lagrangian dual problem and derive an equivalent semi-dual objective that circumvents the need for likelihood estimation. However, the dual problem leads to an unstable min-max training procedure. To alleviate this issue, we further introduce entropy regularization to convert it into a more stable alternative optimization procedure. Based on this, we propose a novel GDA training framework and provide theoretical analysis in terms of stability and generalization. Finally, extensive experiments are conducted to demonstrate the efficacy of the E-SUOT framework. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01179 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Rethinking the Flow-Based Gradual Domain Adaption: A Semi-Dual Optimal Transport Perspective Chen, Zhichao Zhuang, Zhan Teng, Yunfei Wang, Hao Wang, Fangyikang Li, Zhengnan Liu, Tianqiao Li, Haoxuan Lin, Zhouchen Machine Learning Gradual domain adaptation (GDA) aims to mitigate domain shift by progressively adapting models from the source domain to the target domain via intermediate domains. However, real intermediate domains are often unavailable or ineffective, necessitating the synthesis of intermediate samples. Flow-based models have recently been used for this purpose by interpolating between source and target distributions; however, their training typically relies on sample-based log-likelihood estimation, which can discard useful information and thus degrade GDA performance. The key to addressing this limitation is constructing the intermediate domains via samples directly. To this end, we propose an Entropy-regularized Semi-dual Unbalanced Optimal Transport (E-SUOT) framework to construct intermediate domains. Specifically, we reformulate flow-based GDA as a Lagrangian dual problem and derive an equivalent semi-dual objective that circumvents the need for likelihood estimation. However, the dual problem leads to an unstable min-max training procedure. To alleviate this issue, we further introduce entropy regularization to convert it into a more stable alternative optimization procedure. Based on this, we propose a novel GDA training framework and provide theoretical analysis in terms of stability and generalization. Finally, extensive experiments are conducted to demonstrate the efficacy of the E-SUOT framework. |
| title | Rethinking the Flow-Based Gradual Domain Adaption: A Semi-Dual Optimal Transport Perspective |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.01179 |