Gromov-Wasserstein learning for graph matching and node embedding

Hongteng Xu, Dixin Luo, Hongyuan Zha, Lawrence Carin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

A novel Gromov-Wasserstein learning framework is proposed to jointly match (align) graphs and learn embedding vectors for the associated graph nodes. Using Gromov-Wasserstein discrepancy, we measure the dissimilarity between two graphs and find their correspondence, according to the learned optimal transport. The node embeddings associated with the two graphs are learned under the guidance of the optimal transport, the distance of which not only reflects the topological structure of each graph but also yields the correspondence across the graphs. These two learning steps are mutually-beneficial, and are unified here by minimizing the Gromov-Wasserstein discrepancy with structural regularizes. This framework leads to an optimization problem that is solved by a proximal point method. We apply the proposed method to matching problems in real-world networks, and demonstrate its superior performance compared to alternative approaches.
Original languageEnglish (US)
Title of host publication36th International Conference on Machine Learning, ICML 2019
PublisherInternational Machine Learning Society (IMLS)rasmussen@ptd.net
Pages11992-12007
Number of pages16
ISBN (Print)9781510886988
StatePublished - Jan 1 2019
Externally publishedYes

Cite this