Knowledge Graph Completion Based on GCN of Multi-Information Fusion and High-Dimensional Structure Analysis Weight

NIU Haoran; HE Haitao; FENG Jianzhou; NIE Junlan; ZHANG Yangsen; REN Jiadong

doi:10.1049/cje.2021.00.080

Volume 31 Issue 2

Mar. 2022

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2022 > 31(2): 387-396

NIU Haoran, HE Haitao, FENG Jianzhou, et al., “Knowledge Graph Completion Based on GCN of Multi-Information Fusion and High-Dimensional Structure Analysis Weight,” Chinese Journal of Electronics, vol. 31, no. 2, pp. 387-396, 2022, doi: 10.1049/cje.2021.00.080

Citation:

NIU Haoran, HE Haitao, FENG Jianzhou, et al., “Knowledge Graph Completion Based on GCN of Multi-Information Fusion and High-Dimensional Structure Analysis Weight,” Chinese Journal of Electronics, vol. 31, no. 2, pp. 387-396, 2022, doi: 10.1049/cje.2021.00.080

Citation:

PDF( 3691 KB)

Knowledge Graph Completion Based on GCN of Multi-Information Fusion and High-Dimensional Structure Analysis Weight

doi: 10.1049/cje.2021.00.080

1.
Yanshan University, Qinhuangdao 066004, China
2.
Beijing Information Science and Technology University, Beijing 100096, China

Funds: This work was supported by the National Natural Science Foundation of China (61602401,61772449), Scientific and Technological Research Projects of Colleges and Universities in Hebei Province (QN2018074), and Nature Scientist Fund of Hebei Province (F2019203157).

More Information

Author Bio:
was born in 1994. He is currently pursuing Ph.D. degree in software engineering from Yanshan University. His research interests include knowledge graph, natural language processing, and semantic web. (Email: niuhaoran822@163.com)

(corresponding author) was born in 1968. She received the Ph.D. degree in mechanical design and theory from Yanshan University in 2008. She is a Professor at Yanshan University. Her research interests include artificial intelligence and data mining. (Email: haitao@ysu.edu.cn)

was born in 1978. He received the Ph.D. degree from Yanshan University. He is currently an Associate Professor in Yanshan University. His research interests include knowledge graph, natural language processing, and semantic web. (Email: fjzwxh@ysu.edu.cn)

was born in 1962. She received the Ph.D. degree from Hebei University of Technology. She is a Professor in Yanshan University. Her research interests include virtual reality, augmented reality, and data fusion visualization. (Email: niejll3@163.com)

was born in 1962. He received the Ph.D. degree in computer application from Beijing Institute of Technology in 2004. He is a Professor at Beijing Information Science and Technology University. His research interests include artificial intelligence and knowledge engineering. (Email: zhangyangsen@163.com)

was born in 1967. He received the Ph.D. degree in computer application technology from Harbin Institute of Technology in 1999. He is a Professor in Yanshan University. His research interests include data mining, data modeling, and software security. (Email: jdren@ysu.edu.cn)
Received Date: 2021-03-01
Accepted Date: 2021-09-04

Available Online: 2021-11-03

Publish Date: 2022-03-05

Abstract

Abstract

Knowledge graph completion (KGC) can solve the problem of data sparsity in the knowledge graph. A large number of models for the KGC task have been proposed in recent years. However, the underutilisation of the structure information around nodes is one of the main problems of the previous KGC model, which leads to relatively single encoding information. To this end, a new KGC model that encodes and decodes the feature information is proposed. First, we adopt the subgraph sampling method to extract node structure. Moreover, the graph convolutional network (GCN) introduced the channel attention convolution encode node structure features and represent them in matrix form to fully mine the node feature information. Eventually, the high-dimensional structure analysis weight decodes the encoded matrix embeddings and then constructs the scoring function. The experimental results show that the model performs well on the datasets used.
- Knowledge graph completion,
- Graph convolutional network,
- Channel attention convolution,
- High-dimensional structure analysis weight

FullText(HTML)

References(30)

References

[1]	T. Trouillon, J. Welbl, S. Riedel, et al., “Complex embeddings for simple link prediction,” in Proc. of the 33rd Int. Conf. on Machine Learning, New York, USA, pp.2071–2080, 2016.
[2]	B.X. Shi and T. Weninger, “ProjE: Embeddings projection for knowledge graph completion,” in Proc. of the 31st AAAI Conference on Artificial Intelligence, San Francisco, California, USA, pp.1236–1241, 2017.
[3]	B.X. Shi and T. Weninger, “Open-world knowledge graph completion,” in Proc. of the 32nd AAAI Conference on Artificial Intelligence, Louisiana, USA, pp.1957–1964, 2018.
[4]	W. He, Y. Feng, and D. Zhao, “Improving knowledge base completion by incorporating implicit information,” Joint Int. Semantic Technology Conference, Yichang, China, pp.141–153, 2015.
[5]	M. Schlichtkrull, T.N. Kipf, P. Bloem, et al., “Modeling relational data with graph convolutional networks,” European Semantic Web Conference, Heraklion, Crete, Greece, pp.593–607, 2018.
[6]	M. Guillaumin, T. Mensink, J. Verbeek, et al., “Tagprop: Discriminative metric learning in nearest neighbour models for image auto-annotation,” in Proc. of the 12th IEEE International Conference on Computer Vision, kyoto, Japan, pp.309–316, 2009.
[7]	J. Pujara, H. Miao, L. Getoor, et al., “Ontology-aware partitioning for knowledge graph identification,” in Proc. of the 3rd Workshop on Automated Knowledge Base Construction, New York, USA, pp.309–316, 2009.
[8]	N. Bordes, A. Usunier, A. Garcia-Duran, et al., “Translating embeddings for modelling multi-relational data,” in Proc. of the 26th Int. Conf. on Neural Information Processing Systems, New York, USA, pp.2787–2795, 2013.
[9]	Z. Wang, J. Zhang, J. Feng, et al., “Knowledge graph embeddings by translating on hyperplanes,” in Proc. of the 28th AAAI Conference on Artificial Intelligence, Quebec, Canada, pp.1112–1119, 2014.
[10]	G. Ji, S. He, L. Xu, et al., “Knowledge graph embeddings via dynamic mapping matrix,” Meeting of the Association for Computational Linguistics and the International Joint Conference on Natural Language Processing, Beijing, China, pp.687–696, 2015.
[11]	Y. Lin, Z. Liu, M. Sun, et al., “Learning entity and relation embeddings for knowledge graph completion,” in Proc. of the 29th AAAI Conference on Artificial Intelligence, Texas, USA, pp.2181–2187, 2015.
[12]	Y. Jia, Y. Wang, H. Lin, et al., “Locally adaptive translation for knowledge graph embeddings,” in Proc. of the 30th AAAI Conference on Artificial Intelligence, Phoenix, Arizona, USA, pp.992–998, 2016.
[13]	G. Ji, K. Liu, S. He, et al., “Knowledge graph completion with adaptive sparse transfer matrix,” in Proc. of the 30th AAAI Conference on Artificial Intelligence, Phoenix, Arizona, USA, pp.985–991, 2016.
[14]	Dat Quoc Nguyen, Kairit Sirts, Lizhen Qu, et al., “Knowledge graph completion with adaptive sparse transfer matrix,” in Proc. of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, California, USA, pp.460–466, 2016.
[15]	B. Yang, W. Yih, X. He, et al., “Embeddings entities and relations for learning and inference in knowledge bases,” in Proc. of the International Conference on Learning Representations (ICLR), Banff, Canada, pp.1–12, 2014.
[16]	I. Balažević, C. Allen, T.M. Hospedales, et al., “TuckER: Tensor factorization for knowledge graph completion,” in Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th International Joint Conf. on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, pp.5185–5194, 2019.
[17]	M. Nickel, V. Tresp, and H.P. Kriegel, “A three-way model for collective learning on multi-relational data,” in Proc. of the 28th International Conference on Machine Learning, Bellevue, pp.809–816, 2011.
[18]	T. Dettmers, P. Minervini, P. Stenetorp, et al., “Convolutional 2D knowledge graph embeddings,” in Proc. of the 32nd AAAI Conference on Artificial Intelligence, New Orleans, USA, pp.1811–1818, 2018.
[19]	I. Balažević, C. Allen, T.M. Hospedales, et al., “Hypernetwork knowledge graph embeddings,” in Proc. of 28th International Conference on Artificial Neural Networks, Munich, Germany, pp.553–565, 2019.
[20]	A. Tian, C. Zhang, M. Rang, et al., “RA-GCN: Relational aggregation graph convolutional network for knowledge graph completion,” in Proc. of the 12th International Conference on Machine Learning and Computing, Shenzhen, China, pp.580–586, 2020.
[21]	R. Ye, X. Li, Y. Fang, et al., “A vectorized relational graph convolutional network for multi-relational network alignment,” in Proc. of the 28th Int. Joint Conf. on Artificial Intelligence, Macao, China, pp.4135–4141, 2019.
[22]	S. Vashishth, S. Sanyal, V. Nitin, et al., “Composition-based multi-relational graph convolutional networks,” in Proc. of the Int. Conf. on Learning Representations (ICLR), Addis Ababa, Ethiopia, pp.1–15, 2020.
[23]	N. Deepak, J. Chauhan, C. Sharma, et al., “Learning attention-based embeddings for relation prediction in knowledge graphs,” in Proc. of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, pp.4710–4723, 2019.
[24]	J. Wang, Y. Guo, Z. Wang, et al., “Advancing graph convolution network with revised Laplacian matrix,” Chinese Journal of Electronics, vol.29, no.6, pp.1134–1140, 2020. doi: 10.1049/cje.2020.09.015
[25]	L. Yao, C. Mao, Y. Luo, et al., “Graph convolutional networks for text classification,” in Proc. of the 33rd AAAI Conference on Artificial Intelligence, Hawaii, USA, pp.601–610, 2018.
[26]	L. Cai and W.Y. Wang, “KBGAN: Adversarial learning for knowledge graph embeddings,” in Proc. of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, USA, pp.1470–1480, 2018.
[27]	A. Bordes, X. Glorot, J. Weston, et al., “A semantic matching energy function for learning with multi-relational data,” Machine Learning, vol.94, no.2, pp.233–259, 2014. doi: 10.1007/s10994-013-5363-6
[28]	K. Toutanova and D. Chen, “Observed versus latent features for knowledge base and text inference,” in Proc. of the 3rd Workshop on Continuous Vector Space Models and Their Compositionality, Beijing, China, pp.57–66, 2015.
[29]	R. Socher, D. Chen, D. Christopher, et al., “Reasoning with neural tensor networks for knowledge base completion,”in Proc. of the 26th Int. Conf. on Neural Information Processing Systems, New York, USA, pp.926–934, 2013.
[30]	M. Nickel, L. Rosasco, and T. Poggio, “Holographic embeddings of knowledge graphs,” in Proc. of the 30th AAAI Conference on Artificial Intelligence, Phoenix, Arizona, USA, pp.1955–1961, 2016.