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 onrotation and translation in 3D space

在线阅读下载全文

作  者:李子茂[1,2] 汤先毅 尹帆 王灿[1,2] 姜海 Li Zimao;Tang Xianyi;Yin Fan;Wang Can;Jiang Hai(College of Computer Science,South-Central Minzu University,Wuhan 430074,China;Hubei Provincial Engineering Research Center of Agricultural Blockchain&Intelligent Management,Wuhan 430074,China;Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises,Wuhan 430074,China)

机构地区:[1]中南民族大学计算机科学学院,武汉430074 [2]农业区块链与智能管理湖北省工程研究中心,武汉430074 [3]湖北省制造企业智能管理工程技术研究中心,武汉430074

出  处:《计算机应用研究》2024年第1期59-64,共6页Application Research of Computers

基  金:国家民委中青年英才培养计划资助项目(MZR20007);新疆维吾尔自治区区域协同创新专项(科技援疆计划)(2022E02035);武汉市知识创新专项曙光计划资助项目(SZY23003)。

摘  要:现有知识图谱表示学习研究中普遍存在忽视特定关系的语义空间、难以建模非单射复杂关系或多种关系模式等问题,尤其是在不可交换的组合以及子关系两种关系模式上表现不佳。针对该问题,在对实体自适应投影的基础上,利用罗德里格斯旋转公式将旋转操作从二维空间拓展到三维空间并进行平移优化,提出一种新的具有强表征能力的模型ATR3DKRL。通过理论推导可以证明该模型能够建模非单射复杂关系以及多种关系模式。在多个通用数据集上的实验结果表明,该模型可以有效提高链接预测精度,在数据集DB100K与FB15K-237中四个指标上领先现有基线模型,其中在DB100K上评价指标MRR和H@1相较于基线模型RotatE分别大幅提高了3.3%以及6.5%。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 significantly 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 

分 类 号:TP391.1[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象