球面坐标下基于语义分层的知识图谱补全方法

doi:10.3969/j.issn.0255-8297.2024.01.010

摘要/Abstract

摘要： 大多现有知识图谱补全方法普遍忽略了实体间客观存在的语义层次差异，为解决该问题，提出一种在球面坐标系下基于语义分层信息的知识图谱补全（knowledge graphcompletion on semantic hierarchy in spherical coordinates,SpHKC）模型。该方法将实体映射到球面坐标，位于不同球面的实体处于不同语义层级，球的半径越大，该球面上的实体所位于的语义层级越低。而关系则被建模为一个球面的实体向另一实体（位于相同球面或不同球面）的移动，包含旋转与定位操作，以处理实体语义层级异同的两种情况。球面坐标的极角和方位角也给予实体更丰富的表达形式。实验表明，SpHKC与当前主流方法在FB15k-237和WN18RR数据集上的效果基本持平，并且它在YAGO3-10数据集的平均倒数排名（meanreciprocal ranking,MRR）、Hits@10等重要指标上比相关研究的最新算法稳定提升约1%，证明了语义分层信息的有效性。

关键词: 知识图谱, 知识图谱补全, 知识图谱嵌入, 语义层级信息, 语义分层结构, 球坐标

Abstract: Most of existing knowledge graph completion methods often neglect the semantic hierarchical differences that objectively exist between entities. To address these limitations, we propose a knowledge graph completion method named spherical hierarchical knowledge completion (SpHKC), which models semantic hierarchical phenomena using spherical coordinates. In this method, entities are mapped to points on a spherical surface, and entities located on different spheres correspond to different semantic hierarchy levels. The radius of the sphere determines the level of the semantic hierarchy for entities on that sphere, with larger spheres representing lower levels. Relationships are modeled as movements from one entity on the spherical surface to another entity (on the same or different spheres), involving rotation and positioning operations to handle both similar and different semantic hierarchy levels between entities. The polar angle and azimuth angle in spherical coordinates provide entities with richer expressions. Experimental results demonstrate that SpHKC achieves comparable performance to state-of-the-art methods on the FB15k-237 and WN18RR datasets. Moreover, it consistently improves important metrics such as MRR (mean reciprocal ranking) and Hits@10 by approximately 1% compared to recent algorithms on the YAGO3-10 dataset, showcasing the effectiveness of incorporating semantic hierarchical information.

Key words: knowledge graph, knowledge graph completion, knowledge graph embedding, semantic hierarchical information, semantic hierarchy structure, spherical coordinate

中图分类号:

TP391

郭子溢, 朱桐, 林广艳, 谭火彬. 球面坐标下基于语义分层的知识图谱补全方法[J]. 应用科学学报, 2024, 42(1): 119-133.

GUO Ziyi, ZHU Tong, LIN Guangyan, TAN Huobin. Knowledge Graph Completion Method Based on Semantic Hierarchy in Spherical Coordinates[J]. Journal of Applied Sciences, 2024, 42(1): 119-133.

参考文献

[1] Hogan A, Blomqvist E, Cochez M, et al. Knowledge graphs [DB/OL]. 2020[2023-06-29]. https://arxiv.org/abs/2003.02320.
[2] Singhal A. Introducing the knowledge graph: things, not strings [DB/OL]. 2012[2023-06-29]. https://www.blog.google/products/search/introducing-knowledge-graph-things-not/.
[3] Miller G A. WordNet: a lexical database for English [J]. Communications of the ACM, 1995, 38(11): 39-41.
[4] Bollacker K, Tufts P, Pierce T, et al. A platform for scalable, collaborative, structured information integration [C]//Workshop on Information Integration on theWeb (IIWeb'07), 2007: 22-27.
[5] Hoffart J, Suchanek F M, Berberich K, et al. YAGO2: exploring and querying world knowledge in time, space, context, and many languages [C]//The 20th International Conference Companion on World Wide Web, 2011: 229-232.
[6] Vrandecic D, Krötzsch M. Wikidata: a free collaborative knowledgebase [J]. Communications of the ACM, 2014, 57(10): 78-85.
[7] 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.
[8] Huang X, Zhang J Y, Li D C, et al. Knowledge graph embedding based question answering [C]//The Twelfth ACM International Conference on Web Search and Data Mining, 2019: 105-113.
[9] Wang H W, Zhang F Z, Wang J L, et al. RippleNet: propagating user preferences on the knowledge graph for recommender systems [C]//The 27th ACM International Conference on Information and Knowledge Management, 2018: 417-426.
[10] Bordes A, Usunier N, Garcia-Duran A, et al. Translating embeddings for modeling multirelational data [C]//Advances in Neural Information Processing Systems, 2013, 26: 2787-2795.
[11] Wang Z, Zhang J W, Feng J L, et al. Knowledge graph embedding by translating on hyperplanes [C]//The Twenty-Eighth AAAI Conference on Artificial Intelligence, 2014: 1112-1119.
[12] Lin Y K, Liu Z Y, Sun M S, et al. Learning entity and relation embeddings for knowledge graph completion [C]//The Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015: 2181-2187.
[13] Ji G L, He S Z, Xu L H, et al. Knowledge graph embedding via dynamic mapping matrix [C]//The 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, 2015: 687-696.
[14] Jia Y T, Wang Y Z, Lin H L, et al. Locally adaptive translation for knowledge graph embedding [C]//The Thirtieth AAAI Conference on Artificial Intelligence, 2016: 992-998.
[15] Nickel M, Tresp V, Kriegel H P. A three-way model for collective learning on multirelational data [C]//The 28th International Conference on Machine Learning(ICML 2011), 2011: 809-816.
[16] Yang B S, YihWT, He X D, et al. Embedding entities and relations for learning and inference in knowledge bases [DB/OL]. 2020[2023-06-29]. https://arxiv.linfen3.top/abs/1412.6575.
[17] Trouillon T, Welbl J, Riedel S, et al. Complex embeddings for simple link prediction [C]//The 33rd International Conference on Machine Learning, ICML 2016, 2016, 48: 2071-2080.
[18] Nickel M, Rosasco L, Poggio T A. Holographic embeddings of knowledge graphs [C]//The Thirtieth AAAI Conference on Artificial Intelligence, 2016: 1955-1961.
[19] Liu H, Wu Y, Yang Y. Analogical inference for multi-relational embeddings [C]//The 34th International Conference on Machine Learning, 2017, 70: 2168-2178.
[20] Glorot X, Bordes A, Weston J, et al. A semantic matching energy function for learning with multi-relational data [J]//Machine Learning, 2014: 233-259.
[21] Socher R, Chen D Q, Manning C D, et al. Reasoning with neural tensor networks for knowledge base completion [C]//The 26th International Conference on Neural Information Processing Systems, 2013: 926-934.
[22] Dong X, Gabrilovich E, Heitz G, et al. Knowledge vault: a web-scale approach to probabilistic knowledge fusion [C]//The 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014: 601-610.
[23] Dettmers T, Minervini P, Stenetorp P, et al. Convolutional 2D knowledge graph embeddings [C]//The Thirty-Second AAAI Conference on Artificial Intelligence, 2018: 1811-1818.
[24] Nguyen D Q, Nguyen T D, Nguyen D Q, et al. A novel embedding model for knowledge base completion based on convolutional neural network [C]//Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018: 327-333.
[25] Jiang X, Wang Q, Wang B. Adaptive convolution for multi-relational learning [C]//Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 978-987.
[26] Nguyen D Q, Vu T, Nguyen T D, et al. A capsule network-based embedding model for knowledge graph completion and search personalization [C]//Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2019: 2180-2189.
[27] Vashishth S, Sanyal S, Nitin V, et al. InteractE: improving convolution-based knowledge graph embeddings by increasing feature interactions [C]//The Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020: 3009-3016.
[28] Guo L, Sun Z, Hu W. Learning to exploit long-term relational dependencies in knowledge graphs [C]//The 36th International Conference on Machine Learning, 2019, 2505-2514.
[29] Lin Y K, Liu Z Y, Luan H B, et al. Modeling relation paths for representation learning of knowledge bases [C]//Conference on Empirical Methods in Natural Language Processing, 2015: 705-714.
[30] Schlichtkrull M S, Kipf T N, Bloem P, et al. Modeling relational data with graph convolutional networks [C]//European Semantic Web Conference, 2018, 10843: 593-607.
[31] Nathani D, Chauhan J, Sharma C, et al. Learning attention-based embeddings for relation prediction in knowledge graphs [C]//The 57th Conference of the Association for Computational Linguistics, 2019: 4710-4723.
[32] Shang C, Tang Y, Huang J, et al. End-to-end structure-aware convolutional networks for knowledge base completion [C]//AAAI Conference on Artificial Intelligence, 2019, 33(1): 3060-3067.
[33] Sun Z Q, Deng Z H, Nie J Y, et al. RotatE: knowledge graph embedding by relational rotation in complex space [DB/OL]. 2020[2023-06-29]. https://arxiv.org/abs/1902.10197.
[34] Zhang Z, Cai J, Zhang Y, et al. Learning hierarchy-aware knowledge graph embeddings for link prediction [C]//The Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020: 3065-3072.
[35] Gao C, Sun C, Shan L, et al. Rotate3D: representing relations as rotations in threedimensional space for knowledge graph embedding [C]//The 29th ACM International Conference on Information and Knowledge Management, 2020: 385-394.
[36] Xie R, Liu Z, Sun M. Representation learning of knowledge graphs with hierarchical types [C]//The Twenty-Fifth International Joint Conference on Artificial Intelligence, 2016: 2965-2971.
[37] Zhang Z, Zhuang F Z, Qu M, et al. Knowledge graph embedding with hierarchical relation structure [C]//Conference on Empirical Methods in Natural Language Processing, 2018: 3198-3207.
[38] Zhang F X, Wang X, Li Z, et al. TransRHS: a representation learning method for knowledge graphs with relation hierarchical structure [C]//The Twenty-Ninth International Joint Conference on Artificial Intelligence, 2020: 2987-2993.
[39] Vashishth S, Sanyal S, Nitin V, et al. Composition-based multi-relational graph convolutional networks [DB/OL]. 2019[2023-06-29]. https://arxiv.linfen3.top/abs/1911.03082.
[40] Zhang Z Q, Wang J, Ye J P, et al. Rethinking graph convolutional networks in knowledge graph completion [C]//ACM Web Conference 2022, 2022: 798-807.