Many challenges from natural world can be formulated as a graph matching problem. Previous deep learning-based methods mainly consider full two-graph setting. In this work, we study the more general partial problem with multi-graph cycle consistency guarantees. Building on recent progress in learning graphs, propose novel data-driven method (URL) for matching, which uses an object-to-universe f...

We study partial identification of the preference parameters in one-to-one matching model with perfectly transferable utilities. do so without imposing parametric distributional assumptions on unobserved heterogeneity and data one large market. provide a tractable characterization identified set under various classes nonparametric heterogeneity. reexamine some relevant questions empirical liter...