Abstract
Link prediction in signed networks has attracted widespread attention from researchers recently. Existing studies usually learn a representation vector for each node, which is used for link prediction tasks, by aggregating the features of neighbour nodes in the network. However, how to incorporate structural features, e.g., community structure and degree distribution, into graph representation learning remains a difficult challenge. To this end, we propose a novel Structure-enhanced Graph Representation Learning method called SGRL for link prediction in signed networks, which enables the incorporation of structural features into a unified representation. Specifically, the feature of community structure is described by introducing two latent variables to submit to Bernoulli distribution and Gaussian distribution. Moreover, the degree distribution of each node is described by a hidden variable that submits to the Dirichlet distribution by using the community feature as the parameter. Finally, the unified representation obtained from the Dirichlet distribution is further employed for the link prediction based on similarity computation. The effectiveness of the SGRL is demonstrated using benchmark datasets against the state-of-the-art methods in terms of signed link prediction, ablation study, and robustness analysis.
This work is partially supported by the National Natural Science Foundation of China through grants No.61902145 and No. 61902144, the Guangdong Natural Science Foundation (2018A030313339,2021A1515011994), the Scientific Research Team Project of Shenzhen Institute of Information Technology (SZIIT2019KJ022).
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cisneros-Velarde, P., Bullo, F.: Signed network formation games and clustering balance. Dyn. Games Appl. 10(4), 783–797 (2020). https://doi.org/10.1007/s13235-019-00346-8
Tang, J., Aggarwal, C., Liu, H.: Recommendations in signed social networks. In: Proceedings of the 25th International Conference on World Wide Web, pp. 31–40 (2016)
Kunegis, J., Schmidt, S., Lommatzsch, A., Lerner, J., De Luca, E.W., Albayrak, S.: Spectral analysis of signed graphs for clustering, prediction and visualization. Genomics Proteomics Bioinformations 14(1), 62–71 (2016)
Ge, M., Li, A., Wang, M.: A bipartite network-based method for prediction of long non-coding RNA-protein interactions. Bioinformatics 33(4), 608–611 (2017)
Yang, S.H., Smola, J.A., Long, B., Zha, H., Chang, Y.: Friend or frenemy? Predicting signed ties in social networks. In: Proceedings of the ACM Special Interest Group on Information Retrieval (SIGIR), pp. 555–564 (2012)
Chiang, K.Y., Natarajan, N., Tewari, A., Dhillon, S.I.: Exploiting longer cycles for link prediction in signed networks. In: Proceedings of the ACM International Conference on Information and Knowledge Management (CIKM), pp. 1157–1162 (2011)
Patidar, A., Agarwal, V., Bharadwaj, K.K.: Predicting friends and foes in signed networks using inductive inference and social balance theory. In: Proceedings of the IEEE/ACM International Conference on Advances in Social Network Analysis and Mining (ASONAM), pp. 384–388 (2012)
Cygan, M., Pilipczuk, M., Pilipczuk, M., Wojtaszczyk, J.O.: Sitting closer to friends than enemies, revisited. In: Rovan, B., Sassone, V., Widmayer, P. (eds.) MFCS 2012. LNCS, vol. 7464, pp. 296–307. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-32589-2_28
Zolfaghar, K., Aghaie, A.: Mining trust and distrust relationships in social web applications. In: Proceedings of the International Conference on Intelligent Computer Communication and Processing (ICCP), pp. 73–80E (2010)
Borzymek, P., Sydow, M.: Trust and distrust prediction in social network with combined graphical and review-based attributes. In: KES-AMSTA 2010. LNCS (LNAI), vol. 6070, pp. 122–131. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-13480-7_14
Yang, Z., Chen, H., Zhang, J., Ma, J., Yi, C.: Attention-based multi-level feature fusion for named entity recognition. In: Proceedings of the 29th International Joint Conference on Artificial Intelligence (IJCAI), pp. 3594–3600 (2020)
Guha, V.R., Raghavan, P., Tomkins, A., Kumar, R.: Propagation of trust and distrust. In: Proceedings of the International Conference on World Wide Web (WWW), pp. 403–412 (2004)
Kunegis, J., Schmidt, S., Lommatzsch, A., Lerner, J., Luca, W.D.E., Albayrak, S.: Spectral analysis of signed graphs for clustering, prediction and visualization. In: Proceedings of the SIAM International Conference on Data Mining (SDM), pp. 559–570 (2010)
Zhang, H., Wu, G., Ling, Q.: Distributed stochastic gradient descent for link prediction in signed social networks. EURASIP J. Adv. Sig. Process. 2019(1), 1–11 (2019). https://doi.org/10.1186/s13634-019-0601-0
Kim, J., Park, H., Lee, J.E., Kang, U.: Side: representation learning in signed directed networks. In: Proceedings of the International Conference on World Wide Web (WWW), pp. 509–518 (2018)
Wang, S., Tang, J., Aggarwal, C., Chang, Y., Liu, H.: Signed network embedding in social media. In: Proceedings of the SIAM International Conference on Data Mining (SDM), pp. 327–335 (2017)
Islam, M.R., Aditya Prakash, B., Ramakrishnan, N.: SIGNet: scalable embeddings for signed networks. In: Phung, D., Tseng, V.S., Webb, G.I., Ho, B., Ganji, M., Rashidi, L. (eds.) PAKDD 2018. LNCS (LNAI), vol. 10938, pp. 157–169. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-93037-4_13
Derr, T., Ma, Y., Tang, J.: Signed graph convolutional networks. In: Proceedings of the IEEE International Conference on Data Mining (ICDM), pp. 929–934 (2018)
Li, Y., Tian, Y., Zhang, J., Chang, Y.: Learning signed network embedding via graph attention. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 4772–4779 (2020)
Huang, J., Shen, H., Hou, L., Cheng, X.: Signed graph attention networks. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11731, pp. 566–577. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30493-5_53
Eckart, C., Young, G.: The approximation of one matrix by another of lower rank. Psychometrika 1(3), 211–218 (1936)
Maddison, J.C., Mnih, A., Teh, W.Y.: The concrete distribution: a continuous relaxation of discrete random variables. In: Proceedings of the International Conference on Learning Representations (ICLR), pp. 1–20 (2017)
Jang, E., Gu, S., Poole, B.: Categorical reparameterization with gumbel-softmax. In: Proceedings of the International Conference on Learning Representations (ICLR), pp. 1–13 (2017)
Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Proceedings of the International Conference on Learning Representations (ICLR), pp. 1–14 (2014)
Ruiz, J.R.F., Titsias, K.M., Blei, M.D.: The generalized reparameterization gradient. In: Proceedings of the International Conference on Neural Information Processing Systems (NIPS), pp. 460–468 (2016)
Srivastava, A., Sutton, A.C.: Autoencoding variational inference for topic models. In: Proceedings of the International Conference on Learning Representations (ICLR), pp. 1–12 (2017)
Figurnov, M., Mohamed, S., Mnih, A.: Implicit reparameterization gradients. In: Proceedings of the International Conference on Neural Information Processing Systems (NIPS), pp. 439–450 (2018)
Kipf, T.N., Welling, M.: Variational graph auto-encoders. In: Proceedings of the International Conference on Neural Information Processing Systems (NIPS), pp. 1–3 (2016)
Kumar, S., Spezzano, F., Subrahmanian, S.V., Faloutsos, C.: Edge weight prediction in weighted signed networks. In: Proceedings of the IEEE International Conference on Data Mining (ICDM), pp. 221–230 (2016)
Gómez, V., Kaltenbrunner, A., López, V.: Statistical analysis of the social network and discussion threads in slashdot. In: Proceedings of the International Conference on World Wide Web (WWW), pp. 645–654 (2008)
Massa, P., Avesani, P.: Controversial users demand local trust metrics: an experimental study on epinions. com community. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 121–126 (2005)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: Proceedings of the International Conference on Learning Representations (ICLR), pp. 1–14 (2017)
Velickovic, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. In: Proceedings of the International Conference on Learning Representations (ICLR), pp. 1–12 (2018)
Chinchor, N.: MUC-4 evaluation metrics. In: Proceedings of the Conference on Message Understanding (MUC), pp. 22–29 (1992)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Zhang, Y., Yang, Z., Yu, B., Chen, H., Li, Y., Zhao, X. (2021). Structure-Enhanced Graph Representation Learning for Link Prediction in Signed Networks. In: Qiu, H., Zhang, C., Fei, Z., Qiu, M., Kung, SY. (eds) Knowledge Science, Engineering and Management. KSEM 2021. Lecture Notes in Computer Science(), vol 12815. Springer, Cham. https://doi.org/10.1007/978-3-030-82136-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-030-82136-4_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82135-7
Online ISBN: 978-3-030-82136-4
eBook Packages: Computer ScienceComputer Science (R0)