Gromov-Wasserstein Learning for Graph Matching and Node Embedding
Hongteng Xu · Dixin Luo · Hongyuan Zha · Lawrence Carin

Thu Jun 13th 11:25 -- 11:30 AM @ Room 103

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 regularizers. 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.

Author Information

Hongteng Xu (InfiniaML, Inc.)
Dixin Luo (Duke University)
Hongyuan Zha (Georgia Institute of Technology)
Lawrence Carin (Duke)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors