Solving graph compression via optimal transport

Abstract

We propose a new approach to graph compression by appeal to optimal transport. The transport problem is seeded with prior information about node importance, attributes, and edges in the graph. The transport formulation can be setup for either directed or undirected graphs, and its dual characterization is cast in terms of distributions over the nodes. The compression pertains to the support of node distributions and makes the problem challenging to solve directly. To this end, we introduce Boolean relaxations and specify conditions under which these relaxations are exact. The relaxations admit algorithms with provably fast convergence. Moreover, we provide an exact $O(d\log d)$ algorithm for the subproblem of projecting a $d$-dimensional vector to transformed simplex constraints. Our method outperforms state-of-the-art compression methods on graph classification.

References in corpus (8)

• Hierarchical Organization in Complex Networks
• Learning with a Wasserstein Loss
• Projection onto the probability simplex: An efficient algorithm with a simple proof, and an application
• Subgraph Matching Kernels for Attributed Graphs
• The Multiscale Laplacian Graph Kernel
• A Unifying Framework for Spectrum-Preserving Graph Sparsification and Coarsening
• Continuous-Flow Graph Transportation Distances
• Learning SMaLL Predictors

Cited by in corpus (1)

• State-Driven Dynamic Graphon Model