混合曲率空间用于多关系异构知识图谱链接补全

doi:10.11896/jsjkx.220500135

摘要/Abstract

摘要： 知识图谱方法与技术在人工智能领域有较高价值,其面临的一大难题是现有的知识图谱数据集中存在大量边缺失的现象,知识图谱表示学习为解决这一问题提供了解决方案。表示学习的质量取决于嵌入空间的几何形状与数据结构的匹配程度。欧氏空间一直是知识图谱表示学习的主力,而双曲和球面空间因其能够更好地嵌入新类型的结构数据而逐渐受到关注。但大多数数据的异质度较高,单一空间建模可能会导致信息失真较大。为了解决这个问题,受MuRP模型的启发,提出了用混合曲率空间来提供适合各种异质结构数据的表示,用欧氏、双曲和球面空间的笛卡尔积来构造混合空间;设计了混合空间的图注意力机制来获取关系的重要性。在知识图谱3个基准数据集上的实验结果表明,所提模型可以有效缓解异质结构嵌入常曲率低维空间导致的问题。将所提方法应用于推荐系统的冷启动问题上,相应指标均有一定程度的提高。

关键词: 表示学习, 异构知识图谱, 混合曲率空间, 链接预测, 空间权重

Abstract: Knowledge graphs(KGs)has gradually become valuable asset in the field of AI.However,a major problem is that there are many missing edges in the existing KGs.KGs representation learning can effectively solve this problem.The quality of representation learning depends on how well the geometry of the embedding space matches the structure of the data.Euclidean space has been the main force for embeddings;hyperbolic andspherical spaces gaining popularity due to their ability to better embed new types of structured data.However,most data are highly heterogeneous,the single-space modeling leads to large information distortion.To solve this problem,inspired by MuRP model,mixed-curve space model is proposed to provide representations suitable for heterogeneous structural data.Firstly,the Descartes product of Euclidean hyperbolic and spherical spaces is used to construct mixed space.Then,a graph attention mechanism is designed to obtain the importance of relationship.Experimental results on three KGs benchmark datasets show that the proposed model can effectively alleviate the problems caused by heterostructural embedding in low-dimensional spaces with constant curvature.The proposed method is applied to the cold start problem of recommender system,and the corresponding indicators have been improved to a certain extent.

Key words: Representation learning, Heterogeneous knowledge graph, Mixed-curve space, Link prediction, Space weight

中图分类号:

TP391

栗书敬, 黄增峰. 混合曲率空间用于多关系异构知识图谱链接补全[J]. 计算机科学, 2023, 50(4): 172-180. https://doi.org/10.11896/jsjkx.220500135

LI Shujing, HUANG Zengfeng. Mixed-curve for Link Completion of Multi-relational Heterogeneous Knowledge Graphs[J]. Computer Science, 2023, 50(4): 172-180. https://doi.org/10.11896/jsjkx.220500135

参考文献

[1]BERANT J,CHOU A,FROSTIG R,et al.Semantic parsing on freebase from question-answer pairs[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing.2013:1533-1154.
[2]BERANT J,LIANG P.Semantic parsing via paraphrasing[C]//Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics(Volume1:Long Papers).2014:1415-1425.
[3]HE H,BALAKRISHNAN A,ERIC M,et al.Learning symme-tric collaborative dialogue agents with dynamic knowledge graph embeddings[J].arXiv:1704.07130,2017.
[4]KEIZER S,GUHE M,CUAYAHUITL H,et al.Evaluatingpersuasion strategies and deep reinforcement learning methods for negotiation dialogue agents[C]//ACL.2017:480-484.
[5]WANG H,ZHANG F,WANG J,et al.Ripplenet:Propagating user preferences on the Knowledge graph for recommender systems[C]//Proceedings of the 27th ACM International Confe-rence on Information and Knowledge Management.2018:417-426.
[6]WANG X,HE X,CAO Y,et al.Kgat:Knowledge graph attention network for recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Disco-very & Data Mining.2019:950-958.
[7]LIU J,DUAN L.A survey on knowledge graph-based recommender systems[C]//2021 IEEE 5th Advanced Information Technology,Electronic and Automation Control Conference(IAEAC).IEEE,2021:2450-2453.
[8]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Advances in Neural Information Processing Systems.2013:2787-2795.
[9]JI G,HE S,XU L,et al.Knowledge graph embedding via dynamic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing(Volume 1:Long Papers).Beijing,China:Association for Computational Linguistics,2015:687-696.
[10]SUN Z,DENG Z,NIE J,et al.Rotate:Knowledge graph em-bedding by relational rotation in complex space[J/OL].CoRR,2019,abs/190-2.10197.http://arxiv.org/abs/1902.10197.
[11]SARKAR R.Low distortion delaunay embedding of trees in hyperbolic plane[C]//International Symposium on Graph Dra-wing.Berlin／Heidelberg:Springer,2011:355-366.
[12]SALA F,DE SA C,GU A,et al.Representation tradeoffs for hyperbolic embeddings[C]//International Conference on Machine Learning.PMLR,2018:4460-4469.
[13]SAXENA C,CHAUDHARY M,MENG H.Cross-lingual Word Embeddings in Hyperbolic Space[J].arXiv:2205.01907,2022.
[14]MIKOLOV T,YIH W,ZWEIG G.Linguistic regularities in continuous space word representations[C]//Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2013:746-751.
[15]WANG Z,ZHANG J,FENG J,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2014:1112-1119.
[16]LIN Y,LIU Z,SUN M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Twenty-ninth AAAI Conference on Artificial Intelligence.2015:2181-2187.
[17]TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//International Conference on Machine Learning.PMLR,2016:2071-2080.
[18]ZHANG Z,CAI J,ZHANG Y,et al.Learning hierarchy-aware knowledge graph embeddings for link prediction[C]//Procee-dings of the AAAI Conference on Artifical Intelligence.2020:3065-3072.
[19]BALAZEVIC I,ALLEN C,HOSPEDALES T.Multi-relational poincaré graph embeddings[J].Advances in Neural Information Processing System,2019,32:4463-4473.
[20]MONTELLA S,ROJAS-BARAHONA L,HEINECKE J.Hy-perbolic temporal knowledge graph embe-ddings with relational and time curvatures[J].arXiv:2106.04311,2021.
[21]YANG M,ZHOU M,KALANDER M,et al.Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space[C]//Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining.2021:1975-1985.
[22]GUO N,LIU X,LI S,et al.HCGR:Hyperbolic Contrastive Graph Representation Learning for Session-based Recommendation[J].arXiv:2107.05366,2021.
[23]ZHANG S,CHEN H,MING X,et al.Where are we in embedding spaces? A comprehensive analysis on network embedding approaches for recommender systems[J].arXiv:2105.08908,2021.
[24]LI Y,CHEN H,SUN X,et al.Hyperbolic hypergraphs for sequential recommenda-tion[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management.2021:988-997.
[25]YU T,DE SA C.Hyla:Hyperbolic laplacian features for graph learning[J].arXiv:2202.06854,2022.
[26]ZHANG C,GAO J.Hype-han:Hyperbolic hierarchical attention network for semanticembedding[C]//Proceedings of the Twenty-Ninth International Conference on Interna-tional Joint Conferences on Artificial Intelligence.2021:3990-3996.
[27]LIU W,WEN Y,YU Z,et al.Sphereface:Deep hypersphere embedding for face recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:212-220.
[28]WILSON C,HANCOCK E R,PEKALSA E,et al.Spherical and hyperbolic embeddings of data[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2014,36(11):2255-2269.
[29]YANG M,ZHOU M,LI Z,et al.Hyperbolic Graph Neural Networks:A Review of Methods and Applications[J].arXiv:2202.13852,2022.
[30]YANG M,ZHOU M,LIU J,et al.HRCF:Enhancing collaborative filtering via hyperbolic geometric regularization[C]//Proceedings of the ACM Web Conference 2022.2022:2462-2471.
[31]NATHANI D,CHAUHAN J,SHARMA C,et al.Lea-rning attention-based embeddings for relation prediction in knowledge graphs[J].arXiv:1906.01195,2019.
[32]GU A,SALA F,GUNEL B,et al.Learning mixed-curvaturerepresentations in product spaces[C]//International Conference on Learning Representations.2018.
[33]KOPEK O,GANEA O E,BECIGNEUL G.Mixed-curvaturevariational autoencoders[J].arXiv:1911.08411,2019.
[34]FICKEN F A.The riemannian and affine differ-ential geometry of product-spaces[J].Annals of Mathematics,1939,40(4):892-913.
[35]TURAGA P K,SRIVASTAVA A.Riemannian computing incomputer vision:volume 1[M].Springer,2016.
[36]BANSAL T,JUAN D C,RAVI S,et al.A2n:Attending toneighbors for knowledge graph inference[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:4387-4392.
[37]MILLER G A.Wordnet:A lexical database for English[J].Communication of ACM,1995,38(11):39-41.
[38]BOLLACKER K,EVANS C,PARITOSH P,et al.Freebase:A collaboratively created graph database for structuring human knowledge[C]//Proceedings of the 2008 ACM SIGMOD International Conference on Management of Data.2008:1247-1250.
[39]SUCHANEK F M,KASNECIA G,WEIKUM G.Yago:A large ontology from wikipedia and wordnet[J].Journal of Web Semantics,2008,6(3):203-217.
[40]DETTMERS T,MINERVINI P,STENETOPR P,et al.Convolutional 2d knowledge graph embeddings[J/OL].CoRR,2017,abs/1707.01476.http://arxiv.org/abs/1707.01476.
[41]VASHISHTH S,SANYAL S,NITIN V,et al.Composition-based multi-relational graph convolutional networks[J].arXiv:1911.03082,2020.
[42]ZHANG J,SHI X,ZHAO S,et al.Star-gcn:Stac-ked and reconstructed graph convolutional networks for recommender systems[J].arXiv:1905.13129,2019.
[43]MA H,KING I,LYU M R.Effective missing data prediction for collaborative filtering[C]//Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.2007:39-46.
[44]ZHANG F,YUAN N J,LIAN D,et al.Collaborative know-ledge base embedding for recom-mender systems[C]//Procee-dings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.2016:353-362.
[45]WANG Z,LIN G,TAN H,et al.Ckan:collaborative know-ledge-aware attentive network for recommender systems[C]//Proc of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval.2020:219-228.
[46]WANG H,ZHAO M,XIE X,et al.Knowledge graph convolutional networks for recommender systems[C]//The World Wide Web Conference.2019:3307-3313.
[47]CHEN Y,YANG M,ZHANG Y,et al.Modeling scale-freegraphs with hyperbolic geometry for knowledge-aware recommendation[C]//Proceedings of the 15th ACM International Conference on Web Search and Data Mining.2022:94-102.
[48]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.

相关文章 15

[1]	申秋慧, 张宏军, 徐有为, 王航, 程恺. 知识图谱嵌入模型中的损失函数研究综述 Comprehensive Survey of Loss Functions in Knowledge Graph Embedding Models 计算机科学, 2023, 50(4): 149-158. https://doi.org/10.11896/jsjkx.211200175
[2]	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
[3]	李炜卓, 卢冰洁, 杨骏铭, 那崇宁. 基于网络表示学习的车险欺诈溯因分析研究 Study on Abductive Analysis of Auto Insurance Fraud Based on Network Representation Learning 计算机科学, 2023, 50(2): 300-309. https://doi.org/10.11896/jsjkx.220800169
[4]	郝敬宇, 文静轩, 刘华锋, 景丽萍, 于剑. 结合全局信息的深度图解耦协同过滤 Deep Disentangled Collaborative Filtering with Graph Global Information 计算机科学, 2023, 50(1): 41-51. https://doi.org/10.11896/jsjkx.220900255
[5]	宋杰, 梁美玉, 薛哲, 杜军平, 寇菲菲. 基于无监督集群级的科技论文异质图节点表示学习方法 Scientific Paper Heterogeneous Graph Node Representation Learning Method Based onUnsupervised Clustering Level 计算机科学, 2022, 49(9): 64-69. https://doi.org/10.11896/jsjkx.220500196
[6]	黄丽, 朱焱, 李春平. 基于异构网络表征学习的作者学术行为预测 Author’s Academic Behavior Prediction Based on Heterogeneous Network Representation Learning 计算机科学, 2022, 49(9): 76-82. https://doi.org/10.11896/jsjkx.210900078
[7]	徐涌鑫, 赵俊峰, 王亚沙, 谢冰, 杨恺. 时序知识图谱表示学习 Temporal Knowledge Graph Representation Learning 计算机科学, 2022, 49(9): 162-171. https://doi.org/10.11896/jsjkx.220500204
[8]	黄璞, 杜旭然, 沈阳阳, 杨章静. 基于局部正则二次线性重构表示的人脸识别 Face Recognition Based on Locality Regularized Double Linear Reconstruction Representation 计算机科学, 2022, 49(6A): 407-411. https://doi.org/10.11896/jsjkx.210700018
[9]	富坤, 郭云朋, 禚佳明, 李佳宁, 刘琪. 语义增强的完全不平衡标签网络表示学习算法 Semantic Information Enhanced Network Embedding with Completely Imbalanced Labels 计算机科学, 2022, 49(11): 109-116. https://doi.org/10.11896/jsjkx.210900101
[10]	邓亮, 曹存根. 一种专利知识图谱的构建方法 Methods of Patent Knowledge Graph Construction 计算机科学, 2022, 49(11): 185-196. https://doi.org/10.11896/jsjkx.211100063
[11]	蒋宗礼, 樊珂, 张津丽. 基于生成对抗网络和元路径的异质网络表示学习 Generative Adversarial Network and Meta-path Based Heterogeneous Network Representation Learning 计算机科学, 2022, 49(1): 133-139. https://doi.org/10.11896/jsjkx.201000179
[12]	王营丽, 姜聪聪, 冯小年, 钱铁云. 时间感知的兴趣点推荐方法 Time Aware Point-of-interest Recommendation 计算机科学, 2021, 48(9): 43-49. https://doi.org/10.11896/jsjkx.210400130
[13]	赵金龙, 赵中英. 基于异质信息网络表示学习与注意力神经网络的推荐算法 Recommendation Algorithm Based on Heterogeneous Information Network Embedding and Attention Neural Network 计算机科学, 2021, 48(8): 72-79. https://doi.org/10.11896/jsjkx.200800226
[14]	胡昕彤, 沙朝锋, 刘艳君. 基于随机投影和主成分分析的网络嵌入后处理算法 Post-processing Network Embedding Algorithm with Random Projection and Principal Component Analysis 计算机科学, 2021, 48(5): 124-129. https://doi.org/10.11896/jsjkx.200500058
[15]	杨如涵, 戴毅茹, 王坚, 董津. 基于表示学习的工业领域人机物本体融合 Humans-Cyber-Physical Ontology Fusion of Industry Based on Representation Learning 计算机科学, 2021, 48(5): 190-196. https://doi.org/10.11896/jsjkx.200500023

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed