Abstract
Inferring missing facts in temporal knowledge graph (TKG) is a fundamental and challenging task. Existing models typically use representation learning to solve this problem. However, most of these models fall short of capturing multi-hop structural information and general preferences for future emerging facts when implementing the representation of target nodes. In addition, most of them use recurrent neural networks to achieve the aggregation of temporal information, which is not only less scalable as the time step increases, but also fails to explicitly address the problem of temporal sparsity of entity distribution in TKG. To address the above problems, we present a MEFGNN (Multi-view based Entity Frequency-aware Graph Neural Network) framework that learns node embedding to capture structural evolution of TKG by combining Multi-view Graph Neural Network (MGNN) and Entity Frequency-aware Attention Network (EFAN). Experiments on three real datasets show that MEFGNN outperforms state-of-the-art methods, our ablation study also validates the effectiveness of MGNN and EFAN.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anonymous: Learning representation over dynamic graph. arXiv preprint arXiv:2106.01678 (2016)
Jin, W., Qu, M., Jin, X., et al.: Recurrent event network: autoregressive structure inferenceover temporal knowledge graphs. arXiv preprint arXiv:1904.05530 (2020)
Zaremba, W., Sutskever, I., Vinyals, O.: Recurrent neural network regularization. arXiv preprint arXiv:1409.2329 (2014)
Bordes, A., Usunier, N., Garcia-Duran, A., et al.: Translating embeddings for modeling multi-relational data. In: Curran Associates Inc., pp. 1–9 (2013)
Wang, Z., Zhang, J., Feng, J., et al.: Knowledge graph embedding by translating on hyperplanes. In: AAAI, pp. 1112–1119 (2014)
Lin, Y., Liu, Z., Sun, M., Liu, Y., Zhu, X.: Learning entity and relation embeddings for knowledge graph completion. In: AAAI, pp. 2181–2187 (2015)
Li, C., Zhai, R., Zuo, F., Yu, J., Zhang, L.: Mixed multi-channel graph convolution network on complex relation graph. In: Xing, C., Fu, X., Zhang, Y., Zhang, G., Borjigin, C. (eds.) WISA 2021. LNCS, vol. 12999, pp. 497–504. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-87571-8_43
Yang, B., Yih, W, T., He, X., et al.: Embedding entities and relations for learning and inference in knowledge bases. arXiv preprint arXiv:1412.6575 (2014)
Nickel M., et al.: A three-way model for collective learning on multi-relational data. In: International Conference on Machine Learning, pp. 438–445(2011)
Trouillon, T., Welbl, J., Riedel, S., Gaussier, É., Bouchard, G.: Complex embeddings for simple link prediction. In: ICML, pp. 2071–2080 (2016)
Nickel, M., Rosasco, L., Poggio, T.A.: Holographic embeddings of knowledge graphs. In: AAAI, pp. 1955–1961 (2016)
Dettmers, T., Minervini, P., Stenetorp, P., Riedel, S.: Convolutional 2D knowledge graph embeddings. In: AAAI, pp. 1811–1818 (2018)
Seo, Y., Defferrard, M., Vandergheynst, P., Bresson, X.: Structured sequence modeling with graph convolutional recurrent networks. In: Cheng, L., Leung, A.C.S., Ozawa, S. (eds.) ICONIP 2018. LNCS, vol. 11301, pp. 362–373. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-04167-0_33
Schlichtkrull, M., Kipf, T.N., Bloem, P., van den Berg, R., Titov, I., Welling, M.: Modeling relational data with graph convolutional networks. In: Gangemi, A., et al. (eds.) ESWC 2018. LNCS, vol. 10843, pp. 593–607. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93417-4_38
Velikovi, P., et al.: Graph attention networks. arXiv preprint arXiv:1710.10903 (2018)
Jiang, T., et al.: Encoding temporal information for time-aware link prediction. In: EMNLP, pp. 2350–2354 (2016)
Dasgupta, S.S., Ray, S.N., Talukdar, P.P.: HyTE: hyperplane-based temporally aware knowledge graph embedding. In: EMNLP, pp. 2001–2011 (2018)
GarcÃa-Durán, A., Dumani, S., Niepert, M.: Learning sequence encoders for temporal knowledge graph completion. arXiv preprint arXiv:1809.03202 (2018)
Pareja A., Domeniconi G., Chen J., et al.: EvolveGCN: evolving graph convolutional networks for dynamic graphs. arXiv preprint arXiv:1902.10191 (2019)
Sun Z., Deng Z H., Nie J Y., et al.: RotatE: knowledge graph embedding by relational rotation in complex space. arXiv preprint arXiv:1902.10197 (2019)
Kipf, T, N., Welling, M.: Semi-Supervised Classification with Graph Convolutional Networks. arXiv preprint arXiv:1609.02907 (2016)
Cho K., Merrienboer, B, V., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)
Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. arXiv preprint arXiv:1706.03762 (2017)
Acknowledgment
This work was supported by the National Natural Science Foundation of China (62172082, 62072084,62072086), the Fundamental Research Funds for the central Universities (N2116008).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, J., Shen, D., Nie, T., Kou, Y. (2022). Multi-view Based Entity Frequency-Aware Graph Neural Network for Temporal Knowledge Graph Link Prediction. In: Zhao, X., Yang, S., Wang, X., Li, J. (eds) Web Information Systems and Applications. WISA 2022. Lecture Notes in Computer Science, vol 13579. Springer, Cham. https://doi.org/10.1007/978-3-031-20309-1_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-20309-1_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20308-4
Online ISBN: 978-3-031-20309-1
eBook Packages: Computer ScienceComputer Science (R0)