Gromov-Wasserstein Learning for Graph Matching and Node Embedding
This work addresses graph alignment and embedding for network analysis, representing an incremental improvement with a novel hybrid method.
The paper tackles the problem of graph matching and node embedding by proposing a Gromov-Wasserstein learning framework that jointly aligns graphs and learns node embeddings, demonstrating superior performance in real-world network matching compared to alternative approaches.
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.