Get Started
Research questionHow can optimal transport compare network structures while explaining graph-to-graph transformations?Network comparison requires both a measure of structural dissimilarity and an interpretable account of how one graph changes into another. Practitioners need to understand what different optimal-transport distances reveal about these two aspects.
Machine Learning
Research Paper
Statistical Machine Learning
Latest papersRecent research connected to this question, newest first.Optimal Transport for Network Comparison: A Review with Machine Learning ApplicationsThe source reviews Wasserstein, Gromov-Wasserstein, and Bures-Wasserstein distances for network comparison. It discusses one-dimensional Wasserstein distances over node-feature distributions, transport plans that visualize mass shifts, Bures-Wasserstein bounds based on Laplacian spectra, and evaluations on synthetic clustering data and a real-world temporal network.research paper · Sep 2, 2026
Related questions
How can graph neural networks capture long-range interactions without oversmoothing or oversquashing on diverse large graphs?How can we find minimal road-network changes that make a user-selected route optimal?How can graph learning leverage visual graph depictions for structural reasoning?How do architecture and optimization shape accessible representations and scaling at finite budgets on the same data?
Home
Topics
Search
Library