计算机科学

计算机科学 ›› 2025, Vol. 52 ›› Issue (11): 230-236.doi: 10.11896/jsjkx.240800140

• 人工智能 • 上一篇    下一篇

基于变体注意力的关系与属性感知实体对齐

李志康1, 邓怡辰3, 余敦辉1,2, 肖奎1,2   

  1. 1 湖北大学计算机学院 武汉 430062
    2 大数据智能分析与行业应用湖北省重点实验室 武汉 430062
    3 武昌首义学院信息科学与工程学院 武汉 430064
  • 收稿日期:2024-08-26 修回日期:2024-11-26 出版日期:2025-11-15 发布日期:2025-11-06
  • 通讯作者: 邓怡辰(104238327@qq.com)
  • 作者简介:(maplecm@163.com)
  • 基金资助:
    国家自然科学基金(62377009)

Relationship and Attribute Aware Entity Alignment Based on Variant-attention

LI Zhikang1, DENG Yichen3, YU Dunhui1,2, XIAO Kui1,2   

  1. 1 School of Computer Science,Hubei University,Wuhan 430062,China
    2 Hubei Key Laboratory of Big Data Intelligent Analysis and Application(Hubei University),Wuhan 430062, China
    3 School of Information Science and Engineering,Wuchang Shouyi College,Wuhan 430064,China
  • Received:2024-08-26 Revised:2024-11-26 Online:2025-11-15 Published:2025-11-06
  • About author:LI Zhikang,born in 2000,postgraduate.His main research interest is knowledge graph.
    DENG Yichen,born in 1993,postgra-duate,lecturer.Her main research interest is embedded development.
  • Supported by:
    National Natural Science Foundation of China(62377009).

PDF (PC)

27

摘要： 现有的实体对齐方法在区分不同邻居对中心实体的表示作用时,大多利用特征相似性或实体间关系的局部特征信息来计算注意力系数,忽略了关系的全局信息,且不能很好地区分不同信息对实体对齐的作用。为此,提出一种实体对齐模型,根据(关系,邻居)在全图中出现的频率为不同类型的关系分配不同权重,并将该方法融入GAT(Graph Attention Mechanism)中,得到一种变体注意力机制以聚合不同邻居。同时,考虑(属性,属性值)在全图中的频率信息,以类似的方法聚合不同属性值,并将结构和实体名嵌入分别与两种信息结合,得到中心实体的两种嵌入表示。最后,根据实体对在两种嵌入表示上距离的加权进行实体对齐,以考虑关系和属性信息对实体对齐结果的不同影响。实验结果表明,所提模型在DBP15K的3个跨语言数据集上的表现优于其他主流方法,相比最优方法,Hit@1指标最高提升了2.15%,且Hit@10和MRR也均有明显提升,表明该模型能够有效提高实体对齐的准确性。

关键词: 实体对齐, 知识图谱, 变体注意力机制, 属性感知

Abstract: When distinguishing the different representation effects of different neighbors on the central entity,existing entity alignment methods mostly use feature similarity or local feature information of the relationships between entities to calculate attention coefficients.Those methods ignore the global information of relationships,and cannot effectively distinguish the effect of different information on entity alignment.To address this problem,this paper proposes an entity alignment model,which assigns different weights to different types of relationships based on the frequency of(relationship,neighbor) appearing in the entire graph,then integrates the weights into GAT to obtain a variant attention mechanism for aggregating different neighbors.Meanwhile,different attribute values are aggregated in a similar way by using the frequency information of(attributes,attribute values) in the entire graph.After that,combining the structure and entity name embedding with two types of information respectively to obtain two embedding representations of the central entity.Finally,entity alignment is performed based on the weighted distance between the two embedding representations,aims to distinguish the different effects of relationship and attribute information on the entity alignment.Experimental results show that this model is superior to other methods in the three cross lingual datasets of DBP15K,Hit@1 increases by a maximum of 2.15% compare to the optimal method,besides,results also show significant improvement in both Hit@10 and MRR,which indicate that the proposed model can effectively enhance the accuracy of entity alignment.

Key words: Entity alignment, Knowledge graph, Variant attention mechanism, Attribute-aware

中图分类号: 

  • TP391
[1]WANG J,WANG W,MENG F,et al.A Review of Knowledge Reasoning Based on Neural Network[C]//2023 IEEE 12th International Conference on Communication Systems and Network Technologies(CSNT).2023:580-584.
[2]TAHA K,YOO P D,YEUN C,et al.Empirical and experimental perspectives on big data in recommendation systems:a comprehensive survey[J].Big Data Mining and Analytics,2024,7(3):964-1014.
[3]WANG Y,LIPKA N,ROSSI R A,et al.Knowledge graphprompting for multi-document question answering[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2024:19206-19214.
[4]JIANG T,BU C,ZHU Y,et al.Combining embedding-based and symbol-based methods for entity alignment[J].Pattern Recognition,2022,124:108433.
[5]FANOURAKIS N,EFTHYMIOU V,KOTZINOS D,et al.Knowledge graph embedding methods for entity alignment:experimental review[J].Data Mining and Knowledge Discovery,2023,37(5):2070-2137.
[6]SCARSELLI F,GORI M,TSOI A C,et al.The graph neural network model[J].IEEE Transactions on Neural Networks,2008,20(1):61-80.
[7]ZHU B,BAO T,HAN R,et al.An effective knowledge graph entity alignment model based on multiple information[J].Neural Networks,2023,162:83-98.
[8]ZHANG S,TONG H,XU J,et al.Graph convolu- tional networks:a comprehensive review[J].Computational Social Networks,2019,6(1):1-23.
[9]ZHANG Z,YANG Y,CHEN B.Relation-aware heterogeneous graph neural network for entity alignment[J].Neurocomputing,2024,592:127797.
[10]ZHANG F,YANG L Y,LI J W,et al.A Review of EntityAlignment Research [J].Journal of Computer Science,2022,45(6):1195-1225.
[11]ZHU B,WANG R,WANG J,et al.A survey:know- ledge graph entity alignment research based on graph embedding[J].Artificial Intelligence Review,2024,57(9):1-58.
[12]CHEN M,TIAN Y,YANG M,et al.Multilingual Knowledge Graph Embeddings for Cross-lingual Knowledge Alignment[C]//Proceedings of the Twenty-Sixth International Joint Confere-nce on Artificial Intelligence.2017:1511-1517.
[13]SUN Z,HU W,ZHANG Q,et al.Bootstrapping entity alignment with knowledge graph embed-ding[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence.2018:4396-4402.
[14]ZHU B,BAO T,HAN J,et al.Cross-lingual knowledge graphentity alignment by aggregating extensive structures and specific semantics[J].Journal of Ambient Intelligence and Humanized Computing,2023,14(9):12609-12616.
[15]MAO X,WANG W,XU H,et al.MRAEA:an efficient and robust entity alignment approach for cross-lingual knowledge graph[C]//Proceedings of the 13th International Conference on Web Search and Data Mining.2020:420-428.
[16]LIU Z,CAO Y,PAN L,et al.Exploring and Eval-uating Attri-butes,Values,and Structures for Entity Alignment[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.2020:6355-6364.
[17]SHI X,LI B,CHEN L,et al.Bi-Neighborhood Graph Neural Network for cross-lingual entity alignment[J].Knowledge-Based Systems,2023,277:110841.
[18]VELIČKOVIĆ P,CUCURULL G,CASANOVA A,et al.Graph Attention Networks[C]//International Conference on Learning Representations.2018.
[19]RAHIMI A,COHN T,BALDWIN T.Semi-supervised user geolocation via graph convolutional networks[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.2018:2009-2019.
[20]LIN Y,LIU Z,LUAN H,et al.Modeling relation paths for representation learning of knowledge bases[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.2015:705-714.
[21]FORMICA A,TAGLINO F.Semantic relatedness in DBpedia:A comparative and experimental assessment[J].Information Sciences,2023,621:474-505.
[22]WU Y,LIU X,FENG Y,et al.Relation-aware entity alignment for heterogeneous knowledge graphs[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence.2019:5278-5284.
[23]WU Y,LIU X,FENG Y,et al.Jointly Learning Entity and Relation Representations for Entity Alignment[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.2019:240-249.
[24]MAO X,WANG W,WU Y,et al.Boosting the speed of entityalignment 10×:Dual attention matching network with norma-lized hard sample mining[C]//Proceedings of the Web Confe-rence.2021:821-832.
[25]ZHU Y,LIU H,WU Z,et al.Relation-aware neighborhoodmatching model for entity alignment[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:4749-4756.
[26]MAO X,MA M,YUAN H,et al.An effective and efficient entity alignment decoding algorithm via third-order tensor isomorphism[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.2022:5888-5898.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发