ConeE: Global and local context-enhanced embedding for inductive knowledge graph completion

Jingchao Wang, Weimin Li, Fangfang Liu, Zhenhai Wang, Alex Munyole Luvembe, Qun Jin, Quanke Pan, Fangyu Liu

Abstract: Highlights•A multi-granular contextual semantic enhancement method is proposed.•ConeE can fully capture global and local semantic features via GCMM and LCMM.•ConeE can make full use of the induction ability of GNN via IGNN.•Our proposed model achieves SOTA performance on multiple benchmark datasets.