Knowledge Graph Reasoning Based on Paths of Tensor Factorization
WU Yunbing1, ZHU Danhong1, LIAO Xiangwen1,2, ZHANG Dong1, LIN Kaibiao3
1.College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350116 2. Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing,Fuzhou University, Fuzhou 350116 3. College of Computer and Information Engineering, Xiamen University of Technology, Xiamen 361024
Abstract：In the existing tensor factorization techniques used in knowledge graph learning and reasoning, only direct links between entities are taken into account. However, the graph structure of knowledge graph is ignored. In this paper, knowledge graph reasoning based on paths of tensor factorization is proposed. The path ranking algorithm(PRA) is employed to find all paths connecting the source and target nodes in a relation instances. Then, those paths are decomposed by tensor factorization. And the entities and relations are optimized by the alternating least squares method. Experimental results on two large-scale knowledge graphs show the algorithm achieves significant and consistent improvement on tasks of entities linking prediction and paths question answering and its prediction accuracy outperforms that of other related models.
[1] PUJARA J, MIAO H, GETOOR L, et al. Knowledge Graph Identification // Proc of the International Semantic Web Conference. Berlin, Germany: Springer, 2013: 542-557. [2] 刘 峤,李 杨,段 宏,等.知识图谱构建技术综述.计算机研究与发展, 2016, 53(3): 582-600. (LIU Q, LI Y, DUAN H, et al. Knowledge Graph Construction Techniques. Journal of Computer Research and Development, 2016, 53(3): 582-600.) [3] NICKEL M, MURPHY K, TRESP V, et al. A Review of Relational Machine Learning for Knowledge Graphs. Proceedings of the IEEE, 2016, 104(1): 11-33. [4] 刘知远,孙茂松,林衍凯,等.知识表示学习研究进展.计算机研究与发展, 2016, 53(2): 247-261. (LIU Z Y, SUN M S, LIN Y K, et al. Knowledge Representation Learning: A Review. Journal of Computer Research and Development, 2016, 53(2): 247-261.) [5] 刘 康,张元哲,纪国良,等.基于表示学习的知识库问答研究进展与展望.自动化学报, 2016, 42(6): 807-818. (LIU K, ZHANG Y Z, JI G L, et al. Representation Learning for Question Answering over Knowledge Base: An Overview. Acta Automatica Sinica, 2016, 42(6): 807-818.) [6] 吴运兵,杨 帆,赖国华,等.知识图谱学习和推理研究进展.小型微型计算机系统, 2016, 37(9): 2007-2013. (WU Y B, YANG F, LAI G H, et al. Research Progress of Know-ledge Graph Learning and Reasoning. Journal of Chinese Computer Systems, 2016, 37(9): 2007-2013.) [7] NICKEL M, TRESP V, KRIEGEL H P. A Three-Way Model for Collective Learning on Multi-relational Data // Proc of the 28th International Conference on Machine Learning. New York, USA: ACM, 2011: 809-816. [8] NICKEL M, TRESP V, KRIEGEL H P. Factorizing YAGO: Scalable Machine Learning for Linked Data // Proc of the 21st International Conference on World Wide Web. New York, USA: ACM, 2012: 271-280. [9] NICKEL M, TRESP V. Logistic Tensor Factorization for Multi-relational Data[C/OL]. [2016-05-20]. https://arxiv.org/pdf/1306.2084/pdf. [10] NICKEL M, JIANG X Y, TRESP V. Reducing the Rank of Relational Factorization Models by Including Observable Patterns // GHAHRAMANI Z, WELLING M, CORTES C, et al., eds. Advances in Neural Information Processing Systems 27. Cambridge, USA: The MIT Press, 2014: 1179-1187. [11] SOCHER R, CHEN D Q, MANNING C D, et al. Reasoning with Neural Tensor Networks for Knowledge Base Completion // BURGES C J C, BOTTOU L, WELLING M, et al., eds. Advances in Neural Information Processing Systems 26. Cambridge, USA: The MIT Press, 2013: 926-934. [12] CHANG K W, YIH W T, YANG B S, et al. Typed Tensor Decomposition of Knowledge Bases for Relation Extraction // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2014: 1568-1579. [13] KROMPAβ D, NICKEL M, TRESP V. Large-Scale Factorization of Type-Constrained Multi-relational Data // Proc of the International Conference on Data Science and Advanced Analytics. Washington, USA: IEEE, 2014: 18-24. [14] LAO N, MITCHELL T, COHEN W W. Random Walk Inference and Learning in a Large Scale Knowledge Base // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2011: 529-539. [15] NEELAKANTAN A, ROTH B, MCCALLUM A. Compositional Vector Space Models for Knowledge Base Completion // Proc of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2015: 155-166. [16] LIN Y K, LIU Z Y, LUAN H B, et al. Modeling Relation Paths for Representation Learning of Knowledge Bases // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2015: 705-714. [17] YANG B S, YIH W T, HE X D, et al. Embedding Entities and Relations for Learning and Inference in Knowledge Bases[C/OL]. [2016-05-20]. https://arxiv.org/pdf/1412.6575v4.pdf. [18] WANG Q, WANG B, GUO L. Knowledge Base Completion Using Embeddings and Rules // Proc of the 24th International Joint Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2015: 1859-1865. [19] GUU K, MILLER J, LIANG P. Traversing Knowledge Graphs in Vector Space // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2015: 318-327. [20] GARCA-DURN A, BORDES A, USUNIER N. Composing Relationships with Translations // Proc of the Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2015: 286-290. [21] KOLDA T G, BADER B W. Tensor Decompositions and Applications. SIAM Review, 2009, 51(3): 455-500. [22] BORDES A, USUNIER N, GARCIA-DURAN A, et al. Translating Embeddings for Modeling Multi-relational Data // BURGES C J C, BOTTOU L, WELLING M, et al., eds. Advances in Neural Information Processing Systems 26. Cambridge, USA: The MIT Press, 2013: 2787-2795. [23] MILLER G A. WordNet: A Lexical Database for English. Communications of the ACM, 1995, 38(11): 39-41. [24] BOLLACKER K, EVANS C, PARITOSH P, et al. Freebase: A Collaboratively Created Graph Database for Structuring Human Knowledge // Proc of the ACM SIGMOD International Conference on Management of Data. New York, USA: ACM, 2008: 1247-1250.
2017, Vol. 30 
