Abstract
Node classification in temporal graphs aims to predict node labels based on historical observations. In real-world applications, temporal graphs are complex with both graph topology and node attributes evolving rapidly, which poses a high overfitting risk to existing graph learning approaches. In this paper, we propose a novel Temporal Structural Network (TSNet) model, which jointly learns temporal and structural features for node classification from the sparsified temporal graphs. We show that the proposed TSNet learns how to sparsify temporal graphs to favor the subsequent classification tasks and prevent overfitting from complex neighborhood structures. The effective local features are then extracted by simultaneous convolutions in temporal and spatial domains. Using the standard stochastic gradient descent and backpropagation techniques, TSNet iteratively optimizes sparsification and node representations for subsequent classification tasks. Experimental study on public benchmark datasets demonstrates the competitive performance of the proposed model in node classification. Besides, TSNet has the potential to help domain experts to interpret and visualize the learned models.
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
Notes
References
Adhikari, B., Zhang, Y., Amiri, S.E., Bharadwaj, A., Prakash, B.A.: Propagation-based temporal network summarization. IEEE Trans. Knowl. Data Eng. 30(4), 729–742 (2018)
Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271 (2018)
Bruna, J., Zaremba, W., Szlam, A., LeCun, Y.: Spectral networks and locally connected networks on graphs. In: ICLR (2014)
Chen, J., Ma, T., Xiao, C.: Fastgcn: fast learning with graph convolutional networks via importance sampling. In: ICLR (2018)
Ching, A., Edunov, S., Kabiljo, M., Logothetis, D., Muthukrishnan, S.: One trillion edges: graph processing at facebook-scale. Proc. VLDB Endowment 8(12), 1804–1815 (2015)
Defferrard, M., Bresson, X., Vandergheynst, P.: Convolutional neural networks on graphs with fast localized spectral filtering. In: NIPS (2016)
Eden, T., Jain, S., Pinar, A., Ron, D., Seshadhri, C.: Provable and practical approximations for the degree distribution using sublinear graph samples. In: WWW (2018)
Franceschi, L., Niepert, M., Pontil, M., He, X.: Learning discrete structures for graph neural networks. In: ICML (2019)
Ghalebi, E., Mirzasoleiman, B., Grosu, R., Leskovec, J.: Dynamic network model from partial observations. In: NIPS (2018)
Grover, A., Wang, E., Zweig, A., Ermon, S.: Stochastic optimization of sorting networks via continuous relaxations. In: ICLR (2019)
Hamilton, W., Ying, Z., Leskovec, J.: Inductive representation learning on large graphs. In: NIPS (2017)
Hübler, C., Kriegel, H.P., Borgwardt, K., Ghahramani, Z.: Metropolis algorithms for representative subgraph sampling. In: ICDM (2008)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Leskovec, J., Faloutsos, C.: Sampling from large graphs. In: KDD (2006)
Li, J., Cheng, K., Wu, L., Liu, H.: Streaming link prediction on dynamic attributed networks. In: WSDM (2018)
Liu, Y., Safavi, T., Dighe, A., Koutra, D.: Graph summarization methods andapplications: a survey. ACM Comput. Surv. 51(3), 1–34 (2018)
Loukas, A., Vandergheynst, P.: Spectrally approximating large graphs with smaller graphs. In: ICML (2018)
Ma, Y., Guo, Z., Ren, Z., Zhao, E., Tang, J., Yin, D.: Streaming graph neural networks. arXiv:1810.10627v2 (2019)
Maiya, A.S., Berger-Wolf, T.Y.: Sampling community structure. In: WWW (2010)
Mathioudakis, M., Bonchi, F., Castillo, C., Gionis, A., Ukkonen, A.: Sparsification of influence networks. In: KDD (2011)
Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: KDD (2014)
Rong, Y., Huang, W., Xu, T., Huang, J.: Dropedge: towards deep graph convolutional networks on node classification. In: ICLR (2020)
Sadhanala, V., Wang, Y.X., Tibshirani, R.: Graph sparsification approaches for laplacian smoothing. In: AISTATS (2016)
Trivedi, R., Farajtabar, M., Biswal, P., Zha, H.: Dyrep: learning representations over dynamic graphs. In: ICLR (2019)
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)
Wu, Z., Pan, S., Long, G., Jiang, J., Zhang, C.: Graph wavenet for deep spatial-temporal graph modeling. In: IJCAI (2019)
Xu, D., Cheng, W., Luo, D., Liu, X., Zhang, X.: Spatio-temporal attentive RNN for node classification in temporal attributed graphs. In: IJCAI, pp. 3947–3953 (2019)
Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: AAAI (2018)
Yu, B., Yin, H., Zhu, Z.: Spatio-temporal graph convolutional networks: a deep learning framework for traffic forecasting. In: IJCAI (2018)
Yu, W., et al.: Learning deep network representations with adversarially regularized autoencoders. In: KDD (2018)
Zeng, H., Zhou, H., Srivastava, A., Kannan, R., Prasanna, V.: Graphsaint: graph sampling based inductive learning method. In: ICLR (2020)
Zhang, X., Tang, S., Zhao, Y., Wang, G., Zheng, H., Zhao, B.Y.: Cold hard e-cash: friends and vendors in the venmo digital payments system. In: ICWSM (2017)
Zheng, C., Zhang, Q., Long, G., Zhang, C., Young, S.D., Wang, W.: Measuring time-sensitive and topic-specific influence in social networks with lstm and self-attention. IEEE Access 8, 82481–82492 (2020)
Zheng, C., et al.: Robust graph representation learning via neural sparsification. In: ICML (2020)
Zhou, L.K., Yang, Y., Ren, X., Wu, F., Zhuang, Y.: Dynamic network embedding by modeling triadic closure process. In: AAAI (2018)
Acknowledgement
We thank the anonymous reviewers for their careful reading and insightful comments on our manuscript. The work was partially supported by NSF (DGE-1829071, IIS-2031187).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zheng, C. et al. (2021). Node Classification in Temporal Graphs Through Stochastic Sparsification and Temporal Structural Convolution. In: Hutter, F., Kersting, K., Lijffijt, J., Valera, I. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2020. Lecture Notes in Computer Science(), vol 12459. Springer, Cham. https://doi.org/10.1007/978-3-030-67664-3_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-67664-3_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-67663-6
Online ISBN: 978-3-030-67664-3
eBook Packages: Computer ScienceComputer Science (R0)
