The CAT SET on the MAT: Cross Attention for Set Matching in Bipartite Hypergraphs

TL;DR

This paper introduces CATSETMAT, a novel neural network architecture leveraging cross-attention for set matching in bipartite hypergraphs, demonstrating superior performance in link prediction tasks involving complex entity relations.

Contribution

The paper proposes a new cross-attention based model for bipartite hypergraph set matching, addressing higher-order relations beyond traditional hypergraph embeddings.

Findings

CATSETMAT outperforms existing methods on multiple datasets.

The model effectively captures information flow in self- and cross-attention scenarios.

Experimental results validate the superiority of the proposed approach.

Abstract

Usual relations between entities could be captured using graphs; but those of a higher-order -- more so between two different types of entities (which we term "left" and "right") -- calls for a "bipartite hypergraph". For example, given a left set of symptoms and right set of diseases, the relation between a set subset of symptoms (that a patient experiences at a given point of time) and a subset of diseases (that he/she might be diagnosed with) could be well-represented using a bipartite hyperedge. The state-of-the-art in embedding nodes of a hypergraph is based on learning the self-attention structure between node-pairs from a hyperedge. In the present work, given a bipartite hypergraph, we aim at capturing relations between node pairs from the cross-product between the left and right hyperedges, and term it a "cross-attention" (CAT) based model. More precisely, we pose "bipartite hyperedge link prediction" as a set-matching (SETMAT) problem and propose a novel neural network architecture called CATSETMAT for the same. We perform extensive experiments on multiple bipartite hypergraph datasets to show the superior performance of CATSETMAT, which we compare with multiple techniques from the state-of-the-art. Our results also elucidate information flow in self- and cross-attention scenarios.