The CAT SET on the MAT: Cross Attention for Set Matching in Bipartite Hypergraphs
arXiv:2111.00243
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.
arXiv comment18 pages, 9 figures, under review
References in corpus (15)
- The structure and function of complex networks
- Semi-Supervised Classification with Graph Convolutional Networks
- Inductive Representation Learning on Large Graphs
- Social Structure of Facebook Networks
- Simplicial Closure and higher-order link prediction
- Order Matters: Sequence to sequence for sets
- Structural Deep Embedding for Hyper-Networks
- Hypergraph Convolution and Hypergraph Attention
- Latent geometry of bipartite networks
- Hyper-SAGNN: a self-attention based graph neural network for hypergraphs
- On the Limitations of Representing Functions on Sets
- Line Hypergraph Convolution Network: Applying Graph Convolution for Hypergraphs
- Exchangeable deep neural networks for set-to-set matching and learning
- Deep Hyperedges: a Framework for Transductive and Inductive Learning on Hypergraphs
- Powerset Convolutional Neural Networks