AI RESEARCH
CORE: Cyclic Orthotope Relation Embedding for Knowledge Graph Completion
arXiv CS.LG
•
ArXi:2605.11159v1 Announce Type: new Knowledge graph completion (KGC) aims to automatically infer missing facts in multi-relational data by mapping entities and relations into continuous representation spaces. Recent region-based embedding models have shown great promise in capturing complex logical patterns by representing relations as geometric regions. However, these models inevitably suffer from absolute boundary constraints during optimization. Conversely, without such constraints, relation regions expand indefinitely.