文件名称：Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning.pdf
文件大小：1.54MB
文件格式：PDF
更新时间：2022-08-29 08:56:18
KG
Reasoning is essential for the development of large knowledge graphs,especiallyforcompletion,whichaimstoinfernewtriples basedonexistingones.Bothrulesandembeddingscanbeusedfor knowledgegraphreasoningandtheyhavetheirownadvantages anddifficulties.Rule-basedreasoningisaccurateandexplainable butrulelearningwithsearchingoverthegraphalwayssuffersfrom efficiencyduetohugesearchspace.Embedding-basedreasoningis morescalableandefficientasthereasoningisconductedviacomputationbetweenembeddings,butithasdifficultylearninggood representationsforsparseentitiesbecauseagoodembeddingrelies heavilyondatarichness.Basedonthisobservation,inthispaper we explore how embedding and rule learning can be combined together and complement each other’s difficulties with their advantages.WeproposeanovelframeworkIterEiterativelylearning embeddingsandrules,inwhichrulesarelearnedfromembeddings with proper pruning strategy and embeddings are learned from existingtriplesandnewtriplesinferredbyrules.Evaluationson embeddingqualitiesofIterEshowthatruleshelpimprovethequality of sparse entity embeddings and their link prediction results. Wealsoevaluatetheefficiencyofrulelearningandqualityofrules fromIterEcomparedwithAMIE+,showingthatIterEiscapableof generatinghighqualityrulesmoreefficiently.