Partially-Labeled Domain Generalization via Multi-Dimensional Domain Adaptation

Feiyang Ye1; Jianghan Bao2; Yu Zhang1

10.1109/IJCNN54540.2023.10191532

2023

International Joint Conference on Neural Networks (IJCNN)

2161-4393

978-1-6654-8868-6

2023 International Joint Conference on Neural Networks (IJCNN)

2023-June

1-8

18-23 June 2023

Gold Coast, Australia

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Domain generalization deals with a challenging setting where several labeled source domains are given, and the goal is to train machine learning models that can generalize to an unseen test domain. However, in practice, labeled samples are often difficult and expensive to obtain. Thus the source domains would not always be labeled. When only some source domains are labeled and others are unlabeled, we formally introduce this domain generalization problem as Partially-Labeled Domain Generalization (PLDG). In this paper, we study the most challenging setting in PLDG problems, where only one source domain is labeled and a few unlabeled source domains are available. To enable generalization, we assume that all source domains follow certain domain index information that can reflect their domain relationships. With this domain index information, we propose a Multi-Dimensional Domain Adaptation (MDDA) method to address this PLDG problem. Specifically, the MDDA method first trains multiple domain adaptation models to adapt from the labeled source domain to all the unlabeled source domains via adversarial learning. Then those domain adaptation models and the source-only model trained on the labeled source domain only are distilled into the target model used for the unseen target domain. Theoretically, we provide a generalization bound of the MDDA method. The experiments on four real-world datasets demonstrate the effectiveness of the proposed MDDA method.

domain generalization domain adaptation knowledge distillation

第一

英语

CPCI-S ; EI

NSFC[62136005]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Computer Science, Hardware & Architecture ; Engineering, Electrical & Electronic

WOS:001046198703111

20233614678582

Learning systems

Chemical Operations:802.3

IEEE

1.Department of Computer Science and Engineering, Southern University of Science and Technology
2.School of Information Science and Engineering, Southeast University

Feiyang Ye,Jianghan Bao,Yu Zhang. Partially-Labeled Domain Generalization via Multi-Dimensional Domain Adaptation[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2023:1-8.