基于图神经网络的多信息优化实体对齐模型

doi:10.11896/jsjkx.220700242

摘要/Abstract

摘要： 实体对齐是知识融合中的一个关键步骤,旨在发现知识图谱间存在对应关系的实体对。知识图谱融合后可以为下游提供更加广泛而准确的服务。现有的实体对齐模型对实体名称和关系的利用往往不足,在得到实体的向量表示后通过单一的迭代策略或者直接计算得出实体的对齐关系,忽略了部分有用信息,导致实体对齐的结果欠佳。针对上述问题,提出了一种基于图神经网络的多信息优化实体对齐模型。首先,模型的输入融合了实体名称中的单词信息和字符信息,通过注意力机制学习关系的向量表示并利用关系传递信息。在利用实体和关系的预对齐结果修正实体对齐矩阵的基础上,使用延迟接受算法修正部分错误对齐的结果。所提模型在DBP15K的3个子数据集上进行了对比和消融实验。结果表明,相比基线模型,其Hits@1指标分别提高了4.47%,0.82%和0.46%,Hits@10和MRR指标也取得了良好的结果。通过消融实验进一步验证了所提模型的有效性,总体上可以获得更加准确的实体对齐结果。

关键词: 实体对齐, 知识图谱, 图神经网络, 注意力机制, 全局对齐

Abstract: Entity alignment is a key step in knowledge fusion,which aims to discover entity pairs with corresponding relations between knowledge graphs.Knowledge fusion enables a more extensive and accurate services for further knowledge graph applications.However,the entity names and relations are used insufficiently by most of the state-of-the-art models of entity alignment.After obtaining the vector representation of the entity,generally the alignment relations among the entities are obtained through single iterative strategy or direct calculation,while ignoring some valuable information,so that the result of entity alignment is not ideal.In view of the above problems,a multi-information optimized entity alignment model based on graph neural network(MOGNN) is proposed.Firstly,the input of the model fuses word information and character information in the entity name,and the vector representation of relations is learnt through attention mechanism.After transmitting the information by utilizing relations,MOGNN corrects the initial entity alignment matrix based on the pre-alignment results of entities and relations,and finally employs the deferred acceptance algorithm to further correct the misaligned results.The proposed model is validated on three subsets of DBP15K,and compared with the baseline models.Compared with the baseline models,Hits@1 increases by 4.47%,0.82% and 0.46%,Hits@10 and MRR have also achieved impressive results,and the effectiveness of the model is further verifies by ablation experiments.Therefore,more accurate entity alignment results can be obtained with the proposed model.

Key words: Entity alignment, Knowledge graph, Graph neural network, Attention mechanism, Global alignment

中图分类号:

TP391

陈富强, 寇嘉敏, 苏利敏, 李克. 基于图神经网络的多信息优化实体对齐模型[J]. 计算机科学, 2023, 50(3): 34-41. https://doi.org/10.11896/jsjkx.220700242

CHEN Fuqiang, KOU Jiamin, SU Limin, LI Ke. Multi-information Optimized Entity Alignment Model Based on Graph Neural Network[J]. Computer Science, 2023, 50(3): 34-41. https://doi.org/10.11896/jsjkx.220700242

参考文献

[1]WANG H W,ZHANG F Z,ZHAO M,et al.Multi-task feature learning for knowledge graph enhanced recommendation[C]//Proceedings of the World Wide Web Conference.New York:ACM,2019:2000-2010.
[2]CAO Y X,WANG X,HE X G,et al.Unifying knowledge graph learning and recommendation:Towards a better understanding of user preferences[C]//Proceedings of the World Wide Web Conference.New York:ACM,2019:151-161.
[3]SHEN J,QIAO S J,HAN N,et al.Personalized Recommendation Model with Multiple Information Fusion[J].Journal of Chongqing University of Technology(Natural Science),2021,35(3):128-138.
[4]LIU J H,LIN Y K,LIU Z Y,et al.XQA:A Cross-lingual Open-domain Question Answering Dataset[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:ACL,2019:2358-2368.
[5]CHEN X J,XIANG Y.Construction and Application of Enter-prise Risk Knowledge Graph [J].Computer Science,2020,47(11):237-243.
[6]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Transla-ting Embeddings for Modeling Multi-relational Data[C]//Proceedings of Neural Information Processing Systems 26.New York:Curran Associates Inc,2013:2799-2807.
[7]WANG Z C,LV Q S,LAN X H,et al.Cross-lingual knowledgegraph alignment via graph convolutional networks[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.Tokyo:IEICE,2018:349-357.
[8]ROTH A E.Deferred acceptance algorithms:History,theory,practice,and open questions[J].International Journal of Game Theory,2008,36(3/4):537-569.
[9]LEHMANN J,ISELE R,JAKOB M,et al.DBpedia-A Large-scale,Multilingual Knowledge Base Extracted from Wikipedia[J].Semantic Web,2015,6(2):167-195.
[10]JIMENEZ R E,CUENCA G B.Logmap:ogic-based and scalable ontology matching[C]//Proceedings of International Semantic Web Conference.Berlin:Springer,2011:273-288.
[11]LEI J P,OUYANG D T,ZHANG L M.Relation domain and range completion method based on knowledge graph embedding[J].Journal of Jilin University(Engineering and Technology Edition),2022,52(1):154-161.
[12]WANG W J,YU Y F.Automatic completion algorithm for mis-sing links in knowledge graph considering data sparsity[J].Journal of Jilin University(Engineering and Technology Edition),2022,52(6):1428-1433.
[13]WANG S Y,LI X,LI R,et al.Knowledge Fusion Method ofHigh Speed Train Based on Knowledge Graph[J/OL].(2022-07-11) [2022-09-14].https://kns.cnki.net/kcms/detail/51.1277.U.20220711.1502.002.html.
[14]CHEN M H,TIAN Y T,YANG M H,et al.MultilingualKnowledge Graph Embeddings for Cross-lingual Knowledge Alignment[C]//Proceedings of International Joint Conference on Artificial Intelligence.Palo Alto:AAAI Press,2017:1511-1517.
[15]ZHU H,XIE R B,LIU Z Y,et al.Iterative Entity Alignment via Joint Knowledge Embeddings[C]//Proceedings of International Joint Conference on Artificial Intelligence.Palo Alto:AAAI Press,2017:4258-4264.
[16]LIN Y K,LIU Z Y,LUAN H B,et al.Modeling Relation Paths for Representation Learning of Knowledge Bases[C]//Procee-dings of the 2014 Conference on Empirical Methods on Natural Language Processing.Tokyo:IEICE,2015:705-714.
[17]SUN Z Q,HU W,ZHANG Q H,et al.Bootstrapping EntityAlignment with Knowledge Graph Embedding[C]//Proceedings of International Joint Conference on Artificial Intelligence.Palo Alto:AAAI Press,2018:4396-4402.
[18]LI C J,CAO Y X,HOU L,et al.Semi-supervised entity alignment via joint knowledge embedding model and cross-graph model[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.Stroudsburg:ACL,2019:2723-2732.
[19]CAO Y X,LIU Z Y,LI C J,et al.Multi-channel graph neural network for entity alignment[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics.Stroudsburg:ACL,2019:1452-1461.
[20]ZHU Q N,ZHOU X F,WU J,et al.Neighborhood-Aware Attentional Representation for Multilingual Knowledge Graphs[C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence.Palo Alto:AAAI Press,2019:1943-1949.
[21]SUN Z Q,WANG C M.,HU W,et al.Knowledge graph alignment network with gated multi-hop neighborhood aggregation[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Palo Alto:AAAI Press,2020,34(1):222-229.
[22]WU Y T,LIU X,FENG Y S,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.Stroudsburg:ACL,2019:240-249.
[23]WU Y T,LIU X,FENG Y S,et al.Relation-Aware EntityAlignment for Heterogeneous Knowledge Graphs[C]//Procee-dings of Twenty-Eighth International Joint Conference on Artificial Intelligence.Palo Alto:AAAI Press,2019:5278-5284.
[24]ZHU Y,LIU H Z,WU Z H,et al.Relation-Aware Neighborhood Matching Model for Entity Alignment[C]//Proceedings of Database Systems for Advanced Applications－25th International Conference.Berlin:Springer,2021:432-447.
[25]GUO L B,SUN Z Q,HU W.Learning to exploit long-term relational dependencies in knowledge graphs[C]//Proceedings of the 36th International Conference on Machine Learning[C]//Proceedings of the 36th International Conference on Machine Learning.New York:PMLR,2019:2505-2514.
[26]CHEN J,LI Z X,ZHAO P P,et al.Learning Short-Term Diffe-rences and Long-Term Dependencies for Entity Alignment[C]//Proceedings of the International Semantic Web Conference.Berlin:Springer,2020:92-109.
[27]XU K,WANG L W,YU M,et al.Cross-lingual knowledgegraph alignment via graph matching neural network[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics.Stroudsburg:ACL,2019:3156-3161.
[28]ZENG W X,ZHAO X,WANG W,et al.Degree-aware alignment for entities in tail[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.New York:ACM,2020:811-820.
[29]FEY M,LENSSEN J E,MORRIS C,et al.Deep graph matching consensus[C]//Proceedings of the 8th International Conference on Learning Representations.2020:26-30.
[30]SUN Z Q,HU W,LI C K.Cross-lingual entity alignment via joint attribute-preserving embedding[C]//Proceedings of the International Semantic Web Conference.Berlin:Springer,2017:628-644.
[31]NGUYEN T T,HUYNH T T,YIN H Z,et al.Entity Alignment for Knowledge Graphs with Multi-order Convolutional Networks[J].IEEE Transactions on Knowledge and Data Engineering,2022,34(9),4201-4214
[32]ZENG W X,ZHAO X,TANG J Y,et al.Iterative Entity Alignment via Re-Ranking [J].Journal of Computer Research and Development,2020,57(7):1460-1471.
[33]SU J L,WANG Y Z,JIN X L,et al.Entity alignment method based on adaptive attribute selection[J].Journal of Shandong University(Engineering Science),2020,50(1):14-20.
[34]MAO X,WANG W T,WU Y B,et al.From Alignment to Assignment:Frustratingly Simple Unsupervised Entity Alignment[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.Stroudsburg:ACL,2021:2843-2853.
[35]YANG J Z,WAGN D,ZHOU W,et al.Entity and RelationMatching Consensus for Entity Alignment[C]//Proceedings of the 30th ACM International Conference on Information and Knowledge Management.New York:ACM,2021:2331-2341.
[36]SINKHORN R.A relationship between arbitrary positive matrices and doubly stochastic matrices[J].The Annals of Mathematical Statistics,1964,35(2):876-897.
[37]ZHU R B,MA M,WANG P.RAGA:Relation-Aware GraphAttention Networks for Global Entity Alignment[C]//Procee-dings of Pacific-Asia Conference on Knowledge Discovery and Data Mining.Berlin:Springer,2021:501-513.
[38]PENNINGTON J,SOCHER R,MANNING C D.Glove:Global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Proces-sing.Stroudsburg:ACL,2014:1532-1543.

相关文章 15

[1]	李帅, 徐彬, 韩祎珂, 廖同鑫. SS-GCN:情感增强和句法增强的方面级情感分析模型 SS-GCN:Aspect-based Sentiment Analysis Model with Affective Enhancement and Syntactic Enhancement 计算机科学, 2023, 50(3): 3-11. https://doi.org/10.11896/jsjkx.220700238
[2]	马廷淮, 孙圣杰, 荣欢, 钱敏峰. 基于动态记忆和双层重构强化的知识图谱至文本转译模型 Knowledge Graph-to-Text Model Based on Dynamic Memory and Two-layer Reconstruction Reinforcement 计算机科学, 2023, 50(3): 12-22. https://doi.org/10.11896/jsjkx.220700111
[3]	汪璟玢, 赖晓连, 林新宇, 杨心逸. 基于关系约束的上下文感知时态知识图谱补全 Context-aware Temporal Knowledge Graph Completion Based on Relation Constraints 计算机科学, 2023, 50(3): 23-33. https://doi.org/10.11896/jsjkx.220400255
[4]	于健, 赵满坤, 高洁, 王聪源, 李亚蓉, 张文彬. 基于高阶和时序特征的图神经网络社会化推荐算法研究 Study on Graph Neural Networks Social Recommendation Based on High-order and Temporal Features 计算机科学, 2023, 50(3): 49-64. https://doi.org/10.11896/jsjkx.220700108
[5]	刘昕炜, 陶传奇. 一种静态分析与知识图谱结合的Java冗余代码检测方法 Method of Java Redundant Code Detection Based on Static Analysis and Knowledge Graph 计算机科学, 2023, 50(3): 65-71. https://doi.org/10.11896/jsjkx.220700240
[6]	陈姝睿, 梁子然, 饶洋辉. 细粒度语义知识图谱增强的中文OOV词嵌入学习 Fine-grained Semantic Knowledge Graph Enhanced Chinese OOV Word Embedding Learning 计算机科学, 2023, 50(3): 72-82. https://doi.org/10.11896/jsjkx.220700249
[7]	蒋川宇, 韩翔宇, 杨文蕊, 吕博涵, 黄小欧, 谢夏, 谷阳. 医学知识图谱研究与应用综述 Survey of Medical Knowledge Graph Research and Application 计算机科学, 2023, 50(3): 83-93. https://doi.org/10.11896/jsjkx.220700241
[8]	李志飞, 赵月, 张龑. 基于表示学习的知识图谱推理研究综述 Survey of Knowledge Graph Reasoning Based on Representation Learning 计算机科学, 2023, 50(3): 94-113. https://doi.org/10.11896/jsjkx.220900136
[9]	周明强, 代开浪, 吴全旺, 朱庆生. 异构信息网络的注意力感知多通道图卷积评分预测模型 Attention-aware Multi-channel Graph Convolutional Rating Prediction Model for Heterogeneous Information Networks 计算机科学, 2023, 50(3): 129-138. https://doi.org/10.11896/jsjkx.220300004
[10]	冯程程, 刘派, 姜琳颖, 梅笑寒, 郭贵冰. 文档增强型知识库问答 Document-enhanced Question Answering over Knowledge-Bases 计算机科学, 2023, 50(3): 266-275. https://doi.org/10.11896/jsjkx.220300022
[11]	刘泽京, 邬楠, 黄抚群, 宋友. 基于知识图谱与协同过滤混合策略的在线编程评测系统题目推荐模型 Hybrid Programming Task Recommendation Model Based on Knowledge Graph and Collaborative Filtering for Online Judge 计算机科学, 2023, 50(2): 106-114. https://doi.org/10.11896/jsjkx.211200105
[12]	章琪, 于双元, 尹鸿峰, 徐保民. 基于图注意力的神经协同过滤社会推荐算法 Neural Collaborative Filtering for Social Recommendation Algorithm Based on Graph Attention 计算机科学, 2023, 50(2): 115-122. https://doi.org/10.11896/jsjkx.211200019
[13]	邹芸竹, 杜圣东, 滕飞, 李天瑞. 一种基于多模态深度特征融合的视觉问答模型 Visual Question Answering Model Based on Multi-modal Deep Feature Fusion 计算机科学, 2023, 50(2): 123-129. https://doi.org/10.11896/jsjkx.211200303
[14]	王鹏宇, 台文鑫, 刘芳, 钟婷, 罗绪成, 周帆. 基于数据增强的自监督飞行航迹预测 Self-supervised Flight Trajectory Prediction Based on Data Augmentation 计算机科学, 2023, 50(2): 130-137. https://doi.org/10.11896/jsjkx.211200016
[15]	瞿中, 王彩云. 基于注意力机制和轻量级空洞卷积的混凝土路面裂缝检测 Crack Detection of Concrete Pavement Based on Attention Mechanism and Lightweight DilatedConvolution 计算机科学, 2023, 50(2): 231-236. https://doi.org/10.11896/jsjkx.211200290

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed