Margin-aware Adversarial Domain Adaptation with Optimal Transport
Sofien Dhouib, Ievgen Redko, Carole Lartizien
Abstract
In this paper, we propose a new theoretical analysis of unsupervised domain adaptation that relates notions of large margin separation, adversarial learning and optimal transport. This analysis generalizes previous work on the subject by providing a bound on the target margin violation rate, thus reflecting a better control of the quality of separation between classes in the target domain than bounding the misclassification rate. The bound also highlights the benefit of a large margin separation on the source domain for adaptation and introduces an optimal transport (OT) based distance between domains that has the virtue of being task-dependent, contrary to other approaches. From the obtained theoretical results, we derive a novel algorithmic solution for domain adaptation that introduces a novel shallow OT-based adversarial approach and outperforms other OT-based DA baselines on several simulated and real-world classification tasks.
BibTeX
@InProceedings{pmlr-v119-dhouib20b,
title = {Margin-aware Adversarial Domain Adaptation with Optimal Transport},
author = {Dhouib, Sofien and Redko, Ievgen and Lartizien, Carole},
booktitle = {Proceedings of the 37th International Conference on Machine Learning},
pages = {2514--2524},
year = {2020},
editor = {III, Hal Daumé and Singh, Aarti},
volume = {119},
series = {Proceedings of Machine Learning Research},
month = {13--18 Jul},
publisher = {PMLR},
pdf = {http://proceedings.mlr.press/v119/dhouib20b/dhouib20b.pdf},
url = {https://proceedings.mlr.press/v119/dhouib20b.html},
abstract = {In this paper, we propose a new theoretical analysis of unsupervised domain adaptation that relates notions of large margin separation, adversarial learning and optimal transport. This analysis generalizes previous work on the subject by providing a bound on the target margin violation rate, thus reflecting a better control of the quality of separation between classes in the target domain than bounding the misclassification rate. The bound also highlights the benefit of a large margin separation on the source domain for adaptation and introduces an optimal transport (OT) based distance between domains that has the virtue of being task-dependent, contrary to other approaches. From the obtained theoretical results, we derive a novel algorithmic solution for domain adaptation that introduces a novel shallow OT-based adversarial approach and outperforms other OT-based DA baselines on several simulated and real-world classification tasks.}
}