Hypergraphs have attracted increasing attention in recent years thanks to their flexibility in
naturally modeling a broad range of systems where high-order relationships exist among …

Higher-order interactions (HOIs) are ubiquitous in real-world complex systems and
applications. Investigation of deep learning for HOIs, thus, has become a valuable agenda …

Abstract GEnome-scale Metabolic models (GEMs) are powerful tools to predict cellular
metabolism and physiological states in living organisms. However, due to our imperfect …

As a natural extension of link prediction on graphs, hyperlink prediction aims for the
inference of missing hyperlinks in hypergraphs, where a hyperlink can connect more than …

Simplicial neural networks (SNNs) have recently emerged as a new direction in graph
learning which expands the idea of convolutional architectures from node space to simplicial …

Higher-order network models are becoming increasingly relevant for their ability to explicitly
capture interactions between three or more entities in a complex system at once. In this …

Hypergraphs (ie, sets of hyperedges) naturally represent group relations (eg, researchers co-
authoring a paper and ingredients used together in a recipe), each of which corresponds to …

Relations among multiple entities are prevalent in many fields, and hypergraphs are widely
used to represent such group relations. Hence, machine learning on hypergraphs has …

Most of the current hypergraph learning methodologies and benchmarking datasets in the
hypergraph realm are obtained by lifting procedures from their graph analogs …

Cut and spectral sparsification of graphs have numerous applications, including eg
speeding up algorithms for cuts and Laplacian solvers. These powerful notions have …