Expressive Higher-Order Link Prediction through Hypergraph Symmetry Breaking

arXiv:2402.11339v1 Announce Type: new
Abstract: A hypergraph consists of a set of nodes along with a collection of subsets of the nodes called hyperedges. Higher-order link prediction is the task of predicting the existence of a missing hyperedge in a hypergraph. A hyperedge representation learned for higher order link prediction is fully expressive when it does not lose distinguishing power up to an isomorphism. Many existing hypergraph representation learners, are bounded in expressive power by the Generalized Weisfeiler Lehman-1 (GWL-1) …

abstract arxiv breaking collection cs.lg hypergraph link prediction nodes prediction representation set stat.ml symmetry through type