Timezone: »

COPT: Coordinated Optimal Transport on Graphs
Yihe Dong · Will Sawin

Thu Dec 10 09:00 AM -- 11:00 AM (PST) @ Poster Session 5 #1712

We introduce COPT, a novel distance metric between graphs defined via an optimization routine, computing a coordinated pair of optimal transport maps simultaneously. This gives an unsupervised way to learn general-purpose graph representation, applicable to both graph sketching and graph comparison. COPT involves simultaneously optimizing dual transport plans, one between the vertices of two graphs, and another between graph signal probability distributions. We show theoretically that our method preserves important global structural information on graphs, in particular spectral information, and analyze connections to existing studies. Empirically, COPT outperforms state of the art methods in graph classification on both synthetic and real datasets.

Author Information

Yihe Dong (Google)

Machine learning researcher and engineer interested in geometric deep learning, graph representation learning, and natural language processing.

Will Sawin (Columbia University)

More from the Same Authors