计算机应用研究2024，Vol.41Issue(1)：59-64,6.DOI:10.19734/j.issn.1001-3695.2023.05.0282
基于三维空间旋转平移的自适应知识表示方法
Adaptive knowledge representation method based on rotation and translation in 3D space
摘要
Abstract
The existing knowledge graph representation learning studies generally suffer from the problems of neglecting the semantic space of specific relations,or difficulty in modeling non-injective complex relations,or difficulty in modeling multiple relation patterns,especially poor performance on two relation patterns of non-commutative combinations as well as sub-relations.To address this problem,based on the adaptive projection of entities,this paper proposed a new model with strong representation ability,called ATR3DKRL.By extending the rotation operation from 2D to 3D using the Rodrigues'rotation formula with translation optimization,it could be demonstrated through theoretical derivation that the model could model non-injective complex relationships and multiple relation patterns.The experimental results on several generic datasets show that the model can effectively improve link prediction accuracy,leading existing baseline models in four metrics in dataset DB100K and FB15K-237.Comparing to the baseline model RotatE on the evaluation indicators MRR and H@1 in DB100K,it can sig-nificantly increase by 3.3％and 6.5％.关键词
知识图谱/表示学习/自适应投影/旋转平移Key words
knowledge graph/representation learning/adaptive projection/rotation and translation分类
信息技术与安全科学引用本文复制引用
李子茂,汤先毅,尹帆,王灿,姜海..基于三维空间旋转平移的自适应知识表示方法[J].计算机应用研究,2024,41(1):59-64,6.基金项目
国家民委中青年英才培养计划资助项目(MZR20007) （MZR20007）
新疆维吾尔自治区区域协同创新专项(科技援疆计划)(2022E02035) （科技援疆计划）
武汉市知识创新专项曙光计划资助项目(SZY23003) （SZY23003）
