Knowledge Graph Embedding by Double Limit Scoring Loss

Xiaofei Zhou, Lingfeng Niu, Qiannan Zhu, Xingquan Zhu, Ping Liu, Jianlong Tan, Li Guo

2021IEEE Transactions on Knowledge and Data Engineering18 citationsDOI

Abstract

Knowledge graph embedding is an effective way to represent knowledge graph, which greatly enhance the performances on knowledge graph completion tasks, e.g., entity or relation prediction. For knowledge graph embedding models, designing a powerful loss framework is crucial to the discrimination between correct and incorrect triplets. Margin-based ranking loss is a commonly used negative sampling framework to make a suitable margin between the scores of positive and negative triples. However, this loss can not ensure ideal low scores for the positive triplets and high scores for the negative triplets, which is not beneficial for knowledge completion tasks. In this paper, we present a double limit scoring loss to separately set upper bound for correct triplets and lower bound for incorrect triplets, which provides more effective and flexible optimization for knowledge graph embedding. Upon the presented loss framework, we present several knowledge graph embedding models including TransE-SS, TransH-SS, TransD-SS, ProjE-SS and ComplEx-SS. The experimental results on link prediction and triplet classification show that our proposed models have the significant improvement compared to state-of-the-art baselines.

Topics & Concepts

EmbeddingComputer scienceGraphInformation lossUpper and lower boundsMargin (machine learning)Theoretical computer scienceKnowledge graphComputationRanking (information retrieval)Graph embeddingArtificial intelligenceMachine learningAlgorithmMathematicsMathematical analysisAdvanced Graph Neural NetworksBayesian Modeling and Causal InferenceDomain Adaptation and Few-Shot Learning