Neighborhood overlap-aware heterogeneous hypergraph neural network for link prediction

In real world, a large number of networks are heterogeneous, containing different types of semantics and connections. Existing studies typically only consider lower-order pairwise relations rather than higher-order group interactions. Furthermore, they tend to focus more on node attributes rather than graph structural information. This results models failing to maintain graph topology effectively, which reduces the effectiveness on link prediction. To address these limitations, we propose Neighborhood Overlap-aware Heterogeneous hypergraph neural network (NOH) that learns useful structural information from the heterogeneous graph and estimates overlapped neighborhood for link prediction. Our model fuses the heterogeneity of graphs with structural information so that the model maintains both lower-order pairwise relations and higher-order complex semantics. Our extensive experiments on four real-world datasets show that NOH consistently achieves state-of-the-art performance on link prediction.

Automated summary

NOH is a neural network model that utilizes structural information and estimates overlapped neighborhood from a heterogeneous graph for link prediction. It addresses the limitations of existing models that only consider low-order pairwise relations and node attributes, neglecting higher-order group interactions. Experimental results on four real-world datasets demonstrate that NOH consistently achieves state-of-the-art performance on link prediction.