Learning accurate neighborhood- and self-information for higher-order relation prediction in Heterogeneous Information Networks

Jie Li, Xuan Guo, Pengfei Jiao, Wenjun Wang

Abstract: Highlights•We propose ANSE-HGN to solve the problem of higher-order relation prediction in HINs.•We accurately capture the proximity of higher-order relations by multi-hop neighbors.•We design a self-information loss to assist in model optimization.•We conduct experiments on four datasets, demonstrating the effectiveness of ANSE-HGN.