Jointly Learning Explainable Rules for Recommendation with Knowledge Graph.pdf下载

Explainabilityandeffectivenessaretwokeyaspectsforbuildingrecommendersystems.Prioreffortsmostlyfocusonincorporatingside informationtoachievebetterrecommendationperformance.However,thesemethodshavesomeweaknesses:(1)predictionofneural network-basedembeddingmethodsarehardtoexplainanddebug; (2)symbolic,graph-basedapproaches(e.g.,metapath-basedmodels) requiremanualeffortsanddomainknowledgetodefinepatterns andrules,andignoretheitemassociationtypes(e.g.substitutable andcomplementary).Inthispaper,weproposeanoveljointlearningframeworktointegrateinductionofexplainablerulesfromknowledgegraphwithconstructionofarule-guidedneuralrecommendation model. The framework encourages two modules to complement each other in generating effective and explainable recommendation:1)inductiverules,minedfromitem-centricknowledgegraphs, summarizecommonmulti-hoprelationalpatternsforinferringdifferentitemassociationsandprovidehuman-readableexplanation formodelprediction;2)recommendationmodulecanbeaugmented byinducedrulesandthushavebettergeneralizationabilitydealing with the cold-start issue. Extensive experiments1 show that our proposedmethodhasachievedsignificantimprovementsinitem recommendationoverbaselinesonreal-worlddatasets.Ourmodel demonstrates robust performance over “noisy" item knowledge graphs,generatedbylinkingitemnamestorelatedentities.