Hypergraph Co-Optimal Transport: Metric and Categorical Properties

TL;DR

This paper introduces a new theoretical framework for analyzing hypergraphs using optimal transport, defining a hypergraph distance, and exploring transformations between hypergraphs and graphs, with applications in various fields.

Contribution

It develops the Hypergraph Co-Optimal Transport (HyperCOT) framework, establishing metric properties, transformation mappings, and demonstrating its versatility across applications.

Findings

Proposes a hypergraph distance based on co-optimal transport.

Analyzes functorial properties and Lipschitz bounds of hypergraph-to-graph transformations.

Demonstrates the framework's applicability through diverse examples.

Abstract

Hypergraphs capture multi-way relationships in data, and they have consequently seen a number of applications in higher-order network analysis, computer vision, geometry processing, and machine learning. In this paper, we develop theoretical foundations for studying the space of hypergraphs using ingredients from optimal transport. By enriching a hypergraph with probability measures on its nodes and hyperedges, as well as relational information capturing local and global structures, we obtain a general and robust framework for studying the collection of all hypergraphs. First, we introduce a hypergraph distance based on the co-optimal transport framework of Redko et al. and study its theoretical properties. Second, we formalize common methods for transforming a hypergraph into a graph as maps between the space of hypergraphs and the space of graphs, and study their functorial properties and Lipschitz bounds. Finally, we demonstrate the versatility of our Hypergraph Co-Optimal Transport (HyperCOT) framework through various examples.