Abstract
A knowledge graph is a collection of triples, often represented in the form of “subject,” “relation,” “object.” The task of knowledge graph completion (KGC) is to automatically predict missing links by reasoning over the information already present in the knowledge graph. Recent popularization of graph neural networks has also been spread to KGC. Typical techniques like SACN achieve dramatic achievements and beat previous state-of-the-art. However, those models still lack the ability to distinguish different local structures within a graph, which leads to the over smoothing problem. In this work, we propose SD-GAT, a graph attention network with a structure-distinguishable neighborhood aggregation scheme, which models the injective function to aggregate information from the neighborhood. The model is constituted of two modules. The encoder is a graph attention network that improved with our neighborhood aggregation scheme, which could be applied for a more distinct representation of entities and relations. The decoder is a convolutional neural network using \(3\times 3\) convolution filters. Our empirical research provides an effective solution to increase the discriminative power of graph attention networks, and we show significant improvement of the proposed SD-GAT compared to the state-of-the-art methods on standard FB15K-237 and WN18RR datasets.
Similar content being viewed by others
Availability of data and material
All data used during this study are available in the https://github.com/thunlp/OpenKE/tree/master/benchmarks.
References
Suchanek FM, Kasneci G, Weikum G (2007) Yago: a core of semantic knowledge. In: Proceedings of the 16th international conference on World Wide Web, pp 697–706, https://doi.org/10.1145/1242572.1242667
Carlson A, Betteridge J, Kisiel B, Settles B, Hruschka E, Mitchell T (2010) Toward an architecture for never-ending language learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 24
Vrandečić D, Krötzsch M (2014) Wikidata: a free collaborative knowledgebase. Comm ACM 57(10):78–85. https://doi.org/10.1145/2629489
Choi E, Kwiatkowski T, Zettlemoyer L (2015) Scalable semantic parsing with partial ontologies. In: 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), pp 1311–1320, https://doi.org/10.3115/v1/P15-1127
Bordes A, Usunier N, Garcia-Duran A, Weston J, Yakhnenko O (2013) Translating embeddings for modeling multi-relational data. In: Neural Information Processing Systems (NIPS), pp 1–9
Wang Z, Zhang J, Feng J, Chen Z (2014) Knowledge graph embedding by translating on hyperplanes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 28
Lin Y, Liu Z, Sun M, Liu Y, Zhu X (2015) Learning entity and relation embeddings for knowledge graph completion. In: Proceedings of the AAAI Conference on Artificial Intelligence, 29
Trouillon T, Dance CR, Welbl J, Riedel S, Gaussier É, Bouchard G (2017) Knowledge graph completion via complex tensor factorization. arXiv preprint arXiv:170206879
Balažević I, Allen C, Hospedales TM (2019) Tucker: Tensor factorization for knowledge graph completion. arXiv preprint arXiv:190109590 https://doi.org/10.18653/v1/D19-1522
Nguyen DQ, Nguyen TD, Nguyen DQ, Phung D (2017) A novel embedding model for knowledge base completion based on convolutional neural network. arXiv preprint arXiv:171202121 https://doi.org/10.18653/v1/N18-2053
Dettmers T, Minervini P, Stenetorp P, Riedel S (2018) Convolutional 2d knowledge graph embeddings. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 32
Vu T, Nguyen TD, Nguyen DQ, Phung D, et al. (2019) A capsule network-based embedding model for knowledge graph completion and search personalization. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp 2180–2189, https://doi.org/10.18653/v1/N19-1226
Xu K, Li C, Tian Y, Sonobe T, Kawarabayashi Ki, Jegelka S (2018b) Representation learning on graphs with jumping knowledge networks. In: International Conference on Machine Learning, PMLR, pp 5453–5462
Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE (2017) Neural message passing for quantum chemistry. In: International Conference on Machine Learning, PMLR, pp 1263–1272
Schlichtkrull M, Kipf TN, Bloem P, Van Den Berg R, Titov I, Welling M (2018) Modeling relational data with graph convolutional networks. In: European semantic web conference, Springer, pp 593–607
Shang C, Tang Y, Huang J, Bi J, He X, Zhou B (2019) End-to-end structure-aware convolutional networks for knowledge base completion. Proceedings of the AAAI Conference on Artificial Intelligence 33: 3060–3067. https://doi.org/10.1609/AAAI.V33I01.33013060
Veličković P, Cucurull G, Casanova A, Romero A, Lio P, Bengio Y (2017) Graph attention networks. arXiv preprint arXiv:171010903
Thekumparampil KK, Wang C, Oh S, Li LJ (2018) Attention-based graph neural network for semi-supervised learning. arXiv preprint arXiv:180303735
Lee JB, Rossi R, Kong X (2018) Graph classification using structural attention. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 1666–1674
Ji Y, Zhang H, Jie Z, Ma L, Wu QJ (2020) Casnet: a cross-attention siamese network for video salient object detection. IEEE Trans Neural Netw Learn Syst. https://doi.org/10.1109/TNNLS.2020.3007534
Xu K, Hu W, Leskovec J, Jegelka S (2018a) How powerful are graph neural networks? arXiv preprint arXiv:181000826
Weisfeiler B, Leman A (1968) The reduction of a graph to canonical form and the algebra which appears therein. NTI, Series 2(9):12–16
Yang B, Yih Wt, He X, Gao J, Deng L (2014) Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:14126575
Zhang Z, Cai J, Zhang Y, Wang J (2020) Learning hierarchy-aware knowledge graph embeddings for link prediction. Proceed AAAI Conf Artif Intell 34:3065–3072
Nickel M, Tresp V, Kriegel HP (2011) A three-way model for collective learning on multi-relational data. In: Icml
Zhang Z, Cai J, Wang J (2020a) Duality-induced regularizer for tensor factorization based knowledge graph completion. arXiv preprint arXiv:201105816
Sabour S, Frosst N, Hinton GE (2017) Dynamic routing between capsules. arXiv preprint arXiv:171009829
Liang Y, Cai Z, Yu J, Han Q, Li Y (2018) Deep learning based inference of private information using embedded sensors in smart devices. IEEE Netw 32(4):8–14. https://doi.org/10.1109/MNET.2018.1700349
Li K, Lu G, Luo G, Cai Z (2020) Seed-free graph de-anonymiztiation with adversarial learning. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, pp 745–754, https://doi.org/10.1145/3340531.3411970
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:160902907
Nathani D, Chauhan J, Sharma C, Kaul M (2019) Learning attention-based embeddings for relation prediction in knowledge graphs. arXiv preprint arXiv:190601195 https://doi.org/10.18653/v1/P19-1466
Xu X, Feng W, Jiang Y, Xie X, Sun Z, Deng ZH (2019) Dynamically pruned message passing networks for large-scale knowledge graph reasoning. arXiv preprint arXiv:190911334
Bansal T, Juan DC, Ravi S, McCallum A (2019) A2n: Attending to neighbors for knowledge graph inference. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp 4387–4392, https://doi.org/10.18653/v1/P19-14316
Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359–366. https://doi.org/10.1016/0893-6080(89)90020-8
Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4(2):251–257. https://doi.org/10.1016/0893-6080(91)90009-T
Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2017) Attention is all you need. arXiv preprint arXiv:170603762
Kingma DP, Ba J (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980
Toutanova K, Chen D, Pantel P, Poon H, Choudhury P, Gamon M (2015) Representing text for joint embedding of text and knowledge bases. In: Proceedings of the 2015 conference on empirical methods in natural language processing, pp 1499–1509, https://doi.org/10.18653/v1/D15-1174
Cai Z, Zheng X (2018) A private and efficient mechanism for data uploading in smart cyber-physical systems. IEEE Trans Netw Sci Eng 7(2):766–775. https://doi.org/10.1109/TNSE.2018.2830307
Cheng S, Cai Z, Li J, Gao H (2017) Extracting kernel dataset from big sensory data in wireless sensor networks. IEEE Trans Knowl Data Eng 29(4):813–827. https://doi.org/10.1109/TKDE.2016.2645212
Wu Y, Zhang X, Bian Y, Cai Z, Lian X, Liao X, Zhao F (2018) Second-order random walk-based proximity measures in graph analysis: formulations and algorithms. VLDB J 27(1):127–152. https://doi.org/10.1007/s00778-017-0490-5
Acknowledgements
This work was supported by the National Key R&D Program of China (No. 2018YFC0807500), by National Natural Science Foundation of China (No. U19A2059), and by Ministry of Science and Technology of Sichuan Province Program (No. 2018GZDZX0048,20ZDYF0343).
Funding
This work was supported by the National Key \(R \& D\) Program of China (No. 2018YFC0807500), by National Natural Science Foundation of China (No.U19A2059), and by Ministry of Science and Technology of Sichuan Province Program (No.2018GZDZX0048, 20ZDYF0343).
Author information
Authors and Affiliations
Contributions
Xue Zhou and Bei Hui conceived and designed the study. Xue Zhou and Kexi Ji performed the experiments. Xue Zhou wrote the paper. Bei Hui and Lizong Zhang reviewed and edited the manuscript. All authors read and approved the manuscript.
Corresponding author
Ethics declarations
Conflicts of interest/Competing interests
The authors declare that they have no competing interests.
Code availability
All data, models, and code generated or used during the study appear in https://github.com/ooCher/SD-GAT.
Conflict of interest
The authors declare that they do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhou, X., Hui, B., Zhang, L. et al. A structure distinguishable graph attention network for knowledge base completion. Neural Comput & Applic 33, 16005–16017 (2021). https://doi.org/10.1007/s00521-021-06221-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06221-1