SpherE: Expressive and Interpretable Knowledge Graph Embedding for Set Retrieval

arXiv:2404.19130v1 Announce Type: cross
Abstract: Knowledge graphs (KGs), which store an extensive number of relational facts (head, relation, tail), serve various applications. While many downstream tasks highly rely on the expressive modeling and predictive embedding of KGs, most of the current KG representation learning methods, where each entity is embedded as a vector in the Euclidean space and each relation is embedded as a transformation, follow an entity ranking protocol. On one hand, such an embedding design cannot capture many-to-many …

arxiv cs.ai cs.ir cs.lg embedding graph knowledge knowledge graph retrieval set sphere type