基于四元数胶囊网络的知识图谱补全模型

doi:10.19678/j.issn.1000-3428.0060139

摘要/Abstract

摘要： 知识图谱采用RDF三元组的形式描述现实世界中的关系和头、尾实体，即（头实体，关系，尾实体）或（主语，谓语，宾语）。为补全知识图谱中缺失的事实三元组，将四元数融入胶囊神经网络模型预测缺失的知识，并构建一种新的知识图谱补全模型。采用超复数嵌入取代传统的实值嵌入来编码三元组结构信息，以尽可能全面捕获三元组全局特性，将实体、关系的四元数嵌入作为胶囊网络的输入，四元数结合优化的胶囊网络模型可以有效补全知识图谱中丢失的三元组，提高预测精度。链接预测实验结果表明，与CapsE模型相比，在数据集WN18RR中，该知识图谱补全模型的Hit@10与正确实体的倒数平均排名分别提高3.2个百分点和5.5%，在数据集FB15K-237中，Hit@10与正确实体的倒数平均排名分别提高2.5个百分点和4.4%，能够有效预测知识图谱中缺失的事实三元组。

关键词: 知识图谱, 四元数, 胶囊网络, 知识图谱补全, 链接预测

Abstract: Knowledge Graph(KG) uses RDF triplets to describe relationships as well as head and tail entities in the real world, namely (head entity, relationship, tail entity) or (subject, predicate, object).In order to complete the missing fact triplets in knowledge graphs, quaternion is integrated into the capsule neural network model to predict missing knowledge, and on this basis a new knowledge graph completion model is proposed.In order to capture the global features of triplets as much as possible, hypercomplex embedding is used to encode triplet structure information instead of traditional real-valued embedding.In this paper, the quaternion embedding of entities and relationships is used as the input of the capsule network.Quaternion combined with the optimized capsule network model can effectively complete the missing triplets in the knowledge map and improve the prediction accuracy.The proposed model is tested in a link prediction experiment and compared with the CapsE model.Results show that on the WN18RR dataset, the proportion of entities correctly completed by the proposed model is 3.2 percentage points higher than CapsE in Hit@10 and 5.5% higher in the reciprocal average ranking.On the FB15K-237 dataset, the proportion of entities correctly completed by the proposed model is 2.5 percentage points higher in Hit@10 and 4.4% higher in the reciprocal average ranking.The model can effectively predict the missing fact triplets in a knowledge graph.

Key words: Knowledge Graph(KG), quaternion, capsule network, knowledge graph completion, link prediction

中图分类号:

TP18

陈恒, 王思懿, 李冠宇, 祁瑞华, 杨晨, 王维美. 基于四元数胶囊网络的知识图谱补全模型[J]. 计算机工程, 2022, 48(2): 40-46,64.

CHEN Heng, WANG Siyi, LI Guanyu, QI Ruihua, YANG Chen, WANG Weimei. Knowledge Graph Completion Model Based on Quaternion Capsule Network[J]. Computer Engineering, 2022, 48(2): 40-46,64.

http://www.ecice06.com/CN/Y2022/V48/I2/40

图/表 7

20220226124214

20220226124218

20220226124222

20220226124226

20220226124230

20220226124234

20220226124238

参考文献

[1] SUCHANEK F M, KASNECI G, WEIKUM G.YAGO:a core of semantic knowledge[C]//Proceedings of the 16th International Conference on World Wide Web.Washington D.C., USA:IEEE Press, 2007:697-706.
[2] BOLLACKER K, EVANS C, PARITOSH P, et al.Freebase:a collaboratively created graph database for structuring human knowledge[C]//Proceedings of 2008 ACM SIGMOD International Conference on Management of Data.New York, USA:ACM Press, 2008:1247-1250.
[3] 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.
[4] ZHANG F, YUAN N J, LIAN D, et al.Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2016:353-362.
[5] HAO Y, ZHANG Y, LIU K, et al.An end-to-end model for question answering over knowledge base with cross-attention combining global knowledge[C]//Proceedings of the 55th IEEE Annual Meeting of the Association for Computational Linguistics.Washington D.C., USA:IEEE Press, 2017:221-231.
[6] XIONG C, POWER R, CALLAN J.Explicit semantic ranking for academic search via knowledge graph embedding[C]//Proceedings of the 26th IEEE International Conference on World Wide Web.Washington D.C., USA:IEEE Press, 2017:1271-1279.
[7] YANG B, MITCHELL T.Leveraging knowledge bases in lstms for improving machine reading[EB/OL].[2020-10-20].https://arxiv.org/pdf/1902.09091.pdf.
[8] 王维美, 史一民, 李冠宇.改进的胶囊网络知识图谱补全方法[J].计算机工程, 2020, 46(8):21-26. WANG W M, SHI Y M, LI G Y.Improved knowledge graph completion method for capsule network[J].Computer Engineering, 2020, 46(8):21-26.(in Chinese)
[9] 李智星, 任诗雅, 王化明, 等.基于非结构化文本增强关联规则的知识推理方法[J].计算机科学, 2019, 46(11):209-215. LI Z X, REN S Y, WANG H M, et al.Knowledge reasoning method based on unstructured text-enhanced association rules[J].Computer Science, 2019, 46(11):209-215.(in Chinese)
[10] SOCHER R, CHEN D, MANNING C D, et al.Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of NIPSʼ13.Cambridge, USA:MIT Press, 2013:926-934.
[11] WEST R, GABRILOVICH E, MURPHY K, et al.Knowledge base completion via search-based question answering[C]//Proceedings of the 23rd International Conference on World Wide Web.New York, USA:ACM Press, 2014:515-526.
[12] BORDES A, USUNIER N, GARCIA-DURAN A, et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of NIPSʼ13.Cambridge, USA:MIT Press, 2013:2787-2795.
[13] WANG Z, ZHANG J, FENG J, et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.Menlo Park, USA:AAAI Press, 2014:1112-1119.
[14] LIN Y, LIU Z, SUN M, et al.Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of AAAIʼ14.Menlo Park, USA:AAAI Press, 2014:1254-1267.
[15] WANG Q, MAO Z, WANG B, et al.Knowledge graph embedding:a survey of approaches and applications[J].IEEE Transactions on Knowledge and Data Engineering, 2017, 29(12):2724-2743.
[16] 刘知远, 孙茂松, 林衍凯, 等.知识表示学习研究进展[J].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[J].Computer Research and Development, 2016, 53(2):247-261.(in Chinese)
[17] YANG B, YIH W, HE X, et al.Embedding entities and relations for learning and inference in knowledge bases[EB/OL].[2020-10-20].https://arxiv.org/pdf/1412.6575.pdf.
[18] TROUILLON T, WELBL J, RIEDEL S, et al.Complex embeddings for simple link prediction[C]//Proceedings of International Conference on Machine Learning.Washington D.C., USA:IEEE Press, 2016:2071-2080.
[19] NGUYEN D Q, NGUYEN T D, NGUYEN D Q, et al.A novel embeddings model for knowledge base completion based on convolutional neural network[C]//Proceedings of NAACLʼ18.New Orleans, USA:Association for Computational Linguistics, 2018:327-333.
[20] NGUYEN D Q, VU T, NGUYEN T D, et al.A capsule network-based embedding model for knowledge graph completion and search personalization[C]//Proceedings of NAACLʼ19.New Orleans, USA:Association for Computational Linguistics, 2019:2180-2189.
[21] SABOUR S, FROSST N, HINTON G E.Dynamic routing between capsules[C]//Proceedings of NIPSʼ17.Cambridge, USA:MIT Press, 2017:3856-3866.
[22] HINTON G E, SABOUR S, FROSST N.Matrix capsules with EM routing[C]//Proceedings of IEEE International Conference on Learning Representations.Washington D.C., USA:IEEE Press, 2018:235-246.
[23] PARCOLLET T, MORCHID M, LINARES G.Quaternion denoising encoder-decoder for theme identification of telephone conversations[C]//Proceedings of IEEE ISCAʼ17.Washington D.C., USA:IEEE Press, 2017:3325-3328.
[24] GAUDET C, MAIDI A.Deep quaternion networks[C]//Proceedings of 2018 IEEE International Joint Conference on Neural Networks.Washington D.C., USA:IEEE Press, 2017:328-339.
[25] PARCOLLET T, RAVANELLI M, MORCHID M, et al.Quaternion recurrent neural networks[EB/OL].[2020-10-20].https://arxiv.org/pdf/1806.04418.pdf.
[26] 林海伦, 王元卓, 贾岩涛, 等.面向网络大数据的知识融合方法综述[J].计算机学报, 2017, 40(1):3-29. LIN H L, WANG Y Z, JIA Y T, et al.Network big data oriented knowledge fusion methods:a survey[J].Chinese Journal of Computers, 2017, 40(1):3-29.(in Chinese)
[27] 官赛萍, 靳小龙, 贾岩涛, 等.面向知识图谱的知识推理研究进展[J].软件学报, 2018, 29(10):2966-2994. GUAN S P, JIN X L, JIA Y T, et al.Knowledge reasoning over knowledge graph:a survey[J].Journal of Software, 2018, 29(10):2966-2994.(in Chinese)
[28] XIE R B, LIU Z Y, JIA J, et al.Representation learning of knowledge graph with entity descriptions[C]//Proceedings of AAAIʼ16.Cambridge, USA:MIT Press, 2016:2659-2665.
[29] DETTMERS T, MINERVINI P, STENETORP P, et al.Convolutional 2D knowledge graph embeddings[C]//Proceedings of AAAIʼ18.Cambridge, USA:MIT Press, 2018:1811-1818.
[30] CHEN H, WANG W, LI G, et al.A quaternion-embedded capsule network model for knowledge graph completion[J].IEEE Access, 2020, 8:100890-100904.
[31] KINGMA D P, BA J.Adam:a method for stochastic optimization[EB/OL].[2020-10-20].https://arxiv.org/pdf/1412.6980.pdf.
[32] TOUTANOVA K, CHEN D.Observed versus latent features for knowledge base and text inference[C]//Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality.Washington D.C., USA:IEEE Press, 2015:57-66.
[33] SUN Z, DENG Z H, NIE J Y, et al.Rotate:knowledge graph embedding by relational rotation in complex space[EB/OL].[2020-10-20].https://arxiv.org/pdf/1902.10197.pdf.
[34] NGUYEN D Q, NGUYEN D Q, NGUYEN T D, et al.A convolutional neural network-based model for knowledge base completion and its application to search personalization[J].Semantic Web, 2019, 10(5):947-960.
[35] 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.Washington D.C., USA:IEEE Press, 2015:687-696.

选择文件类型/文献管理软件名称

选择包含的内容