Margin-aware Adversarial Domain Adaptation with Optimal Transport

Sofien Dhouib, Ievgen Redko, Carole Lartizien
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:2514-2524, 2020.

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.

Cite this Paper

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.} }
Endnote
%0 Conference Paper %T Margin-aware Adversarial Domain Adaptation with Optimal Transport %A Sofien Dhouib %A Ievgen Redko %A Carole Lartizien %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-dhouib20b %I PMLR %P 2514--2524 %U https://proceedings.mlr.press/v119/dhouib20b.html %V 119 %X 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.
APA
Dhouib, S., Redko, I. & Lartizien, C.. (2020). Margin-aware Adversarial Domain Adaptation with Optimal Transport. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:2514-2524 Available from https://proceedings.mlr.press/v119/dhouib20b.html.

Related Material