Link Prediction on Dynamic Heterogeneous Information Networks
Abstract
This work develops a broad learning method for link prediction on dynamic heterogeneous information networks. While existing works have primarily focused on dynamic homogeneous networks or static heterogeneous networks. As such, the existing methods can be suboptimal for link prediction on dynamic heterogeneous information networks.
In this paper, we try to study the problem of link prediction combining dynamic networks and heterogeneous networks. However, none of the existing works has paid special attention to connect these two kinds of network data. To tackle this challenge, we propose a new broad learning-based method named HA-LSTM, short for Hierarchical Attention Long-Short Time Memory to address this problem on dynamic heterogeneous information networks. Firstly, we employ the Graph Convolutional Network (GCN) to extract the feature from Heterogeneous Information Networks (HINs). Then, we utilize a broad learning and attention based framework to fuse and extract the information among HINs broadly over timestamps. Finally, the link prediction in time-dimension by employing LSTM could be performed. We conduct extensive experiments on several real dynamic heterogeneous information networks covering the task of link prediction. Both quantitative results and qualitative analysis verify the effectiveness and rationality of our HA-LSTM method.
Keywords
Dynamic heterogeneous information network Link prediction Broad learningReferences
- 1.Zhao, A., Zhao, L., Yu, Y.: The joint framework for dynamic topic semantic link network prediction. IEEE Access 7, 7409–7418 (2019)CrossRefGoogle Scholar
- 2.Manzoor, E., Milajerdi, S.M., Akoglu, L.: Fast memory efficient anomaly detection in streaming heterogeneous graphs. In: Proceedings of ACM SIGKDD International Conference of Knowledge Discovery and Data Mining, pp. 1035–1044. ACM, San Francisco (2016)Google Scholar
- 3.Liu, L., et al.: ABNE: an attention-based network embedding for user alignment across social networks. IEEE Access 7, 23595–23605 (2019)CrossRefGoogle Scholar
- 4.Tang, J., et al.: LINE: large-scale information network embedding. In: Proceedings of ACM WWW International World Wide Web Conferences, pp. 1067–1077. ACM, Florence (2015)Google Scholar
- 5.Grover, A., Leskovec, J.: node2vec: scalable feature learning for networks. In: Proceedings of ACM SIGKDD International Conference of Knowledge Discovery and Data Mining, pp. 855–864. ACM, San Francisco (2016)Google Scholar
- 6.Liben-Nowell, D., Kleinberg, J.M.: The link prediction problem for social networks. In: Proceedings of ACM CIKM International Conference on Information and Knowledge Management, pp. 556–559. ACM, New Orleans (2003)Google Scholar
- 7.Dong, Y., Chawla, N.V., Swami, A.: metapath2vec: scalable representation learning for heterogeneous networks. In: Proceedings of ACM SIGKDD International Conference of Knowledge Discovery and Data Mining, pp. 135–144. ACM, Halifax (2017)Google Scholar
- 8.Li, J., et al.: Meta-path based heterogeneous combat network link prediction. Phys. A 482, 507–523 (2017)MathSciNetCrossRefGoogle Scholar
- 9.Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: Proceedings of ACM SIGKDD International Conference of Knowledge Discovery and Data Mining, pp. 701–710. ACM, New York (2014)Google Scholar
- 10.Richardson, M., Domingos, P.M.: The intelligent surfer: probabilistic combination of link and content information in PageRank. In: Proceedings of Annual Conference on Neural Information Processing Systems, pp. 1441–1448. MIT Press, Vancouver (2001)Google Scholar
- 11.Jeh, G., Widom, J.: SimRank: a measure of structural-context similarity. In: Proceedings of ACM SIGKDD International Conference of Knowledge Discovery and Data Mining, pp. 538–543. ACM, Edmonton (2002)Google Scholar
- 12.Wang, D., Cui, P., Zhu, W.: Structural deep network embedding. In: Proceedings of ACM SIGKDD International Conference of Knowledge Discovery and Data Mining, pp. 1225–1234. ACM, San Francisco (2016)Google Scholar
- 13.Cao, S., Lu, W., Xu, Q.: Deep neural networks for learning graph representations. In: Proceedings of AAAI Conference on Artificial Intelligence, pp. 1145–1152. AAAI, Phoenix (2016)Google Scholar
- 14.Niepert, M., Ahmed, M., Kutzkov, K.: Learning convolutional neural networks for graphs. In: Proceedings of ACM International Conference on Machine Learning, pp. 2014–2023. ACM, New York (2016)Google Scholar
- 15.Goyal, P., Ferrara, E.: Graph embedding techniques, applications, and performance: a survey. Knowl. Based Syst. 151, 78–94 (2018)CrossRefGoogle Scholar
- 16.Zhang, J., Yu, P.S.: Broad learning: an emerging area in social network analysis. SIGKDD Explor. 20(1), 24–50 (2018)CrossRefGoogle Scholar
- 17.Cao, B., Mao, M., Viidu, S., Yu, P.S.: HitFraud: a broad learning approach for collective fraud detection in heterogeneous information networks. In: Proceedings of ACM International Conference on Data Mining, pp. 769–774. New Orleans (2017)Google Scholar
- 18.Zhang, J., et al.: BL-ECD: broad learning based enterprise community detection via hierarchical structure fusion. In: Proceedings of ACM CIKM International Conference on Information and Knowledge Management, pp. 859–868. ACM, Singapore (2017)Google Scholar
- 19.Zhu, J., Zhang, J., et al.: Broad learning based multisource collaborative recommendation. In: Proceedings of ACM CIKM International Conference on Information and Knowledge Management, pp. 1409–1418. ACM, Singapore (2017)Google Scholar
- 20.Hammond, D.K., Vandergheynst, P., Gribonval, R.: Wavelets on graphs via spectral graph theory. Appl. Comput. Harmonic Anal. 30(2), 129–150 (2011)MathSciNetCrossRefGoogle Scholar
- 21.Wang, P., Niamat, M., Vemuru, S.: Majority logic synthesis based on Nauty algorithm. In: Anderson, N.G., Bhanja, S. (eds.) Field-Coupled Nanocomputing. LNCS, vol. 8280, pp. 111–132. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-43722-3_6CrossRefGoogle Scholar
- 22.Tong, T., Li, G., Liu, X., Gao, Q.: Image super-resolution using dense skip connections. In: Proceedings of IEEE International Conference on Computer Vision, pp. 4809–4817. IEEE, Venice (2017)Google Scholar
- 23.Du, L., Wang, Y., Song, G., Lu, Z., Wang, J.: Dynamic network embedding : an extended approach for skip-gram based network embedding. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 2086–2092. Morgan Kaufmann, Stockholm (2018)Google Scholar