Abstract
Graphs have become widely adopted as a means of representing relationships between entities in many applications. These graphs often evolve over time. Learning effective representations preserving graph topology, as well as latent patterns in temporal dynamics, has drawn increasing interests. In this paper, we investigate the problem of dynamic graph embedding that maps a time series of graphs to a low dimensional feature space. However, most existing works in the field of dynamic representation learning either consider temporal evolution of low-order proximity or treat high-order proximity and temporal dynamics separately. It is challenging to learn one single embedding that can preserve the high-order proximity with long-term temporal dependencies. We propose a Generative Adversarial Networks (GAN) based model, named DynGraphGAN, to learn robust feature representations. It consists of a generator and a discriminator trained in an adversarial process. The generator generates connections between nodes that are represented by a series of adjacency matrices. The discriminator integrates a graph convolutional network for high-order proximity and a convolutional neural network for temporal dependency to distinguish real samples from fake samples produced by the generator. With iterative boosting of the performance of the generator and discriminator, node embeddings are learned to present dynamic evolution over time. By jointly considering high-order proximity and temporal evolution, our model can preserve spatial structure with temporal dependency. DynGraphGAN is optimized on subgraphs produced by random walks to capture more complex structural and temporal patterns in the dynamic graphs. We also leverage sparsity and temporal smoothness properties to further improve the model efficiency. Our model demonstrates substantial gains over several baseline models in link prediction and reconstruction tasks on real-world datasets.
Keywords
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Following settings in related work, we only consider discrete-time dynamic graphs since we can take discrete snapshots from a continuously varying graph. This is also the case of many real applications where recording every changes is expensive or unnecessary, e.g., brain networks and bibliographic networks.
- 2.
- 3.
- 4.
- 5.
References
Barkan, O., Koenigstein, N.: ITEM2VEC: neural item embedding for collaborative filtering. In: IEEE International Workshop on Machine Learning for Signal Processing, pp. 1–6 (2016)
Bojchevski, A., Shchur, O., Zügner, D., Günnemann, S.: NetGAN: generating graphs via random walks. arXiv preprint arXiv:1803.00816 (2018)
Cao, S., Lu, W., Xu, Q.: GraREP: learning graph representations with global structural information, pp. 891–900 (2015)
Ciresan, D.C., Giusti, A., Gambardella, L.M., Schmidhuber, J.: Deep neural networks segment neuronal membranes in electron microscopy images. In: Neural Information Processing Systems, pp. 2852–2860 (2012)
Dai, Q., Li, Q., Tang, J., Wang, D.: Adversarial network embedding. In: AAAI Conference on Artificial Intelligence, pp. 2167–2174 (2018)
Donahue, J., Krähenbühl, P., Darrell, T.: Adversarial feature learning. arXiv preprint arXiv:1605.09782 (2016)
Faloutsos, C., McCurley, K.S., Tomkins, A.: Fast discovery of connection subgraphs. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 118–127 (2004)
Fawcett, T.: An introduction to ROC analysis. Pattern Recogn. Lett. 27, 861–874 (2006)
Glover, J.: Modeling documents with generative adversarial networks. arXiv preprint arXiv:1612.09122 (2016)
Goodfellow, I., et al.: Generative adversarial nets. In: Neural Information Processing Systems, pp. 2672–2680 (2014)
Goyal, P., Kamra, N., He, X., Liu, Y.: DynGEM: deep embedding method for dynamic graphs. In: IJCAI International Workshop on Representation Learning for Graphs (2017)
Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 855–864 (2016)
Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of Wasserstein GANs. In: Neural Information Processing Systems, pp. 5769–5779 (2017)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)
Hogg, T., Lerman, K.: Social dynamics of digg. arXiv preprint arXiv:1202.0031 (2012)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907 (2016)
Koren, Y., North, S.C., Volinsky, C.: Measuring and extracting proximity graphs in networks. ACM Trans. Knowl. Discov. Data 1, 12 (2007)
Leskovec, J., Kleinberg, J.M., Faloutsos, C.: Graphs over time: densification laws, shrinking diameters and possible explanations. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 177–187 (2005)
Li, B., Zheng, C., Huang, D., Zhang, L., Han, K.: Gene expression data classification using locally linear discriminant embedding. Comput. Biol. Med. 40, 802–810 (2010)
Liao, L., He, X., Zhang, H., Chua, T.S.: Attributed social network embedding. arXiv preprint arXiv:1705.04969 (2017)
Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: ICML Workshop on Deep Learning for Audio, Speech and Language Processing, p. 3 (2013)
Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Neural Information Processing Systems, pp. 3111–3119 (2013)
Ou, M., Cui, P., Pei, J., Zhang, Z., Zhu, W.: Asymmetric transitivity preserving graph embedding. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1105–1114 (2016). https://doi.org/10.1145/2939672.2939751
Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Empirical Methods in Natural Language Processing, pp. 1532–1543 (2014)
Perozzi, B., Al-Rfou, R., Skiena, S.: DeepWalk: online learning of social representations. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 701–710 (2014)
Sasaki, Y., et al.: The truth of the F-measure. Teach Tutor mater 1, 1–5 (2007)
Viswanath, B., Mislove, A., Cha, M., Gummadi, K.P.: On the evolution of user interaction in Facebook. In: ACM Workshop on Online Social Networks, pp. 37–42 (2009)
Wang, D., Cui, P., Zhu, W.: Structural deep network embedding. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1225–1234 (2016)
Wang, H., et al.: GraphGAN: graph representation learning with generative adversarial nets. In: AAAI Conference on Artificial Intelligence, pp. 2508–2515 (2018)
Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)
Yang, C., Sun, M., Liu, Z., Tu, C.: Fast network embedding enhancement via high order proximity approximation. In: International Joint Conference on Artificial Intelligence, pp. 3894–3900 (2017)
Yu, W., Cheng, W., Aggarwal, C.C., Chen, H., Wang, W.: Link prediction with spatial and temporal consistency in dynamic networks. In: International Joint Conference on Artificial Intelligence, pp. 3343–3349 (2017)
Zhou, L., Yang, Y., Ren, X., Wu, F., Zhuang, Y.: Dynamic network embedding by modelling triadic closure process. In: AAAI Conference on Artificial Intelligence, pp. 571–578 (2018)
Zhu, D., Cui, P., Zhang, Z., Pei, J., Zhu, W.: High-order proximity preserved embedding for dynamic networks. IEEE Trans. Knowl. Data Eng. 30, 2134–2144 (2018)
Zhu, L., Guo, D., Yin, J., Steeg, G.V., Galstyan, A.: Scalable temporal latent space inference for link prediction in dynamic social networks. IEEE Trans. Knowl. Data Eng. 28, 2765–2777 (2016)
Acknowledgements
This work is supported in part by the National Natural Science Foundation of China Projects No. U1636207, No. 91546105, the Shanghai Science and Technology Development Fund No. 16JC1400801, No. 17511105502, No. 17511101702.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Xiong, Y., Zhang, Y., Fu, H., Wang, W., Zhu, Y., Yu, P.S. (2019). DynGraphGAN: Dynamic Graph Embedding via Generative Adversarial Networks. In: Li, G., Yang, J., Gama, J., Natwichai, J., Tong, Y. (eds) Database Systems for Advanced Applications. DASFAA 2019. Lecture Notes in Computer Science(), vol 11446. Springer, Cham. https://doi.org/10.1007/978-3-030-18576-3_32
Download citation
DOI: https://doi.org/10.1007/978-3-030-18576-3_32
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-18575-6
Online ISBN: 978-3-030-18576-3
eBook Packages: Computer ScienceComputer Science (R0)