Gromov-Wasserstein Learning for Graph Matching and Node Embedding

By Hongteng Xu, Dixin Luo, Hongyuan Zha, Lawrence Carin. International Conference on Machine Learning, 2019

323 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/f20049425c119f65cb7273e0abb1e48e848905b7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Zhe Gan
2. Linjie Li
3. Jingjing Liu
4. Yu Cheng
5. Lawrence Carin
6. Jianfeng Gao
7. Chunyuan Li
8. Mohit Bansal

In Computer Vision and Pattern Recognition

1. Zhe Gan
2. Linjie Li
3. Jingjing Liu
4. Yu Cheng
5. Lawrence Carin
6. Chunyuan Li
7. Jianfeng Gao
8. Dacheng Tao

In Molecular Biology

1. Zhe Gan
2. Lawrence Carin
3. Yu Cheng
4. Jingjing Liu
5. René Vidal

Citations in the corpus

• Graph Optimal Transport for Cross-Domain Alignment (2020, methodology): “Instead of using projected gradient descent or conjugated gradient descent as in Xu et al. (2019b;a); Vayer et al. (2018), we can approximate the transport plan T by adding back L unified in Algorithm 2, so that Line 9 in Algorithm 2 helps solve T for WD and GWD at the same time, effectively…”