Open-Set Graph Domain Adaptation via Separate Domain Alignment
DOI:
https://doi.org/10.1609/aaai.v38i8.28765Keywords:
DMKM: Graph Mining, Social Network Analysis & Community, ML: Transfer, Domain Adaptation, Multi-Task Learning, KRR: Other Foundations of Knowledge Representation & ReasoningAbstract
Domain adaptation has become an attractive learning paradigm, as it can leverage source domains with rich labels to deal with classification tasks in an unlabeled target domain. A few recent studies develop domain adaptation approaches for graph-structured data. In the case of node classification task, current domain adaptation methods only focus on the closed-set setting, where source and target domains share the same label space. A more practical assumption is that the target domain may contain new classes that are not included in the source domain. Therefore, in this paper, we introduce a novel and challenging problem for graphs, i.e., open-set domain adaptive node classification, and propose a new approach to solve it. Specifically, we develop an algorithm for efficient knowledge transfer from a labeled source graph to an unlabeled target graph under a separate domain alignment (SDA) strategy, in order to learn discriminative feature representations for the target graph. Our goal is to not only correctly classify target nodes into the known classes, but also classify unseen types of nodes into an unknown class. Experimental results on real-world datasets show that our method outperforms existing methods on graph domain adaptation.Downloads
Published
2024-03-24
How to Cite
Wang, Y., Zhu, R., Ji, P., & Li, S. (2024). Open-Set Graph Domain Adaptation via Separate Domain Alignment. Proceedings of the AAAI Conference on Artificial Intelligence, 38(8), 9142-9150. https://doi.org/10.1609/aaai.v38i8.28765
Issue
Section
AAAI Technical Track on Data Mining & Knowledge Management