Orthogonal Gromov-Wasserstein Discrepancy with Efficient Lower BoundDownload PDF

Published: 20 May 2022, Last Modified: 05 May 2023UAI 2022 PosterReaders: Everyone
Keywords: metric geometry, optimal transportation
TL;DR: We propose a surrogate of Gromov-Wasserstein discrepancy which is effective for machine learning, and provides tight and efficient lower bounds.
Abstract: Comparing structured data from possibly different metric-measure spaces is a fundamental task in machine learning, with applications in, e.g., graph classification. The Gromov-Wasserstein (GW) discrepancy formulates a coupling between the structured data based on optimal transportation, tackling the incomparability between different structures by aligning the intra-relational geometries. Although efficient \emph{local} solvers such as conditional gradient and Sinkhorn are available, the inherent non-convexity still prevents a tractable evaluation, and the existing lower bounds are not tight enough for practical use. To address this issue, we take inspirations from the connection with the quadratic assignment problem, and propose the orthogonal Gromov-Wasserstein (OGW) discrepancy as a surrogate of GW. It admits an efficient and \emph{closed-form} lower bound with $\mathcal{O}(n^3)$ complexity, and directly extends to the fused Gromov-Wasserstein distance, incorporating node features into the coupling. Extensive experiments on both the synthetic and real-world datasets show the tightness of our lower bounds, and both OGW and its lower bounds efficiently deliver accurate predictions and satisfactory barycenters for graph sets.
Supplementary Material: zip
6 Replies