文件名称：RotatE：Knowledge Graph Embedding by Relational Rotation in Complex Space.pdf
文件大小：661KB
文件格式：PDF
更新时间：2022-08-29 09:03:20
KG
We study the problem of learning representations of entities and relations in knowledgegraphsforpredictingmissinglinks. Thesuccessofsuchataskheavily relies on the ability of modeling and inferring the patterns of (or between) the relations. Inthispaper,wepresentanewapproachforknowledgegraphembedding called RotatE, which is able to model and infer various relation patterns including: symmetry/antisymmetry,inversion,andcomposition. Specifically,theRotatE modeldefineseachrelationasarotationfromthesourceentitytothetargetentity inthecomplexvectorspace. Inaddition,weproposeanovelself-adversarialnegativesamplingtechniqueforefficientlyandeffectivelytrainingtheRotatEmodel. Experimentalresultsonmultiplebenchmarkknowledgegraphsshowthattheproposed RotatE model is not only scalable, but also able to infer and model various relation patterns and significantly outperform existing state-of-the-art models for link prediction.