On the Network Embedding in Sparse Signed Networks

  • Ayan Kumar BhowmickEmail author
  • Koushik Meneni
  • Bivas Mitra
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11441)


Network embedding, that learns low-dimensional node representations in a graph such that the network structure is preserved, has gained significant attention in recent years. Most state-of-the-art embedding methods have mainly designed algorithms for representing nodes in unsigned social networks. Moreover, recent embedding approaches designed for the sparse real-world signed networks have several limitations, especially in the presence of a vast majority of disconnected node pairs with opposite polarities towards their common neighbors. In this paper, we propose sign2vec, a deep learning based embedding model designed to represent nodes in a sparse signed network. sign2vec leverages on signed random walks to capture the higher-order neighborhood relationships between node pairs, irrespective of their connectivity. We design a suitable objective function to optimize the learned node embeddings such that the link forming behavior of individual nodes is captured. Experiments on empirical signed network datasets demonstrate the effectiveness of embeddings learned by sign2vec for several downstream applications while outperforming state-of-the-art baseline algorithms.


Signed network embedding Autoencoders Conflicting node pairs 


  1. 1.
    Grover, A., Leskovec, J.: node2vec: scalable feature learning for networks. In: KDD, pp. 855–864 (2016)Google Scholar
  2. 2.
    Hsieh, C.-J., Chiang, K.-Y., Dhillon, I.S.: Low rank modeling of signed networks. In: KDD, pp. 507–515 (2012)Google Scholar
  3. 3.
    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). Scholar
  4. 4.
    Jung, J., Jin, W., Sael, L., Kang, U.: Personalized ranking in signed networks using signed random walk with restart. In: ICDM, pp. 973–978 (2016)Google Scholar
  5. 5.
    Kim, J., Park, H., Lee, J.-E., Kang, U.: Side: representation learning in signed directed networks. In: WWW, pp. 509–518 (2018)Google Scholar
  6. 6.
    Leskovec, J., Huttenlocher, D., Kleinberg, J.: Signed networks in social media. In: SIGCHI, pp. 1361–1370 (2010)Google Scholar
  7. 7.
    Van Der Maaten, L., Hinton, G.: Visualizing data using t-SNE. JMLR 9, 2579–2605 (2008)zbMATHGoogle Scholar
  8. 8.
    Perozzi, B., Al-Rfou, R., Skiena, S.: Deepwalk: online learning of social representations. In: KDD, pp. 701–710 (2014)Google Scholar
  9. 9.
    Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., Mei, Q.: Line: large-scale information network embedding. In: WWW, pp. 1067–1077 (2015)Google Scholar
  10. 10.
    Wang, D., Cui, P., Zhu, W.: Structural deep network embedding. In: KDD, pp. 1225–1234 (2016)Google Scholar
  11. 11.
    Wang, S., Aggarwal, C., Tang, J., Liu, H.: Attributed signed network embedding. In: CIKM, pp. 137–146 (2017)Google Scholar
  12. 12.
    Wang, S., Tang, J., Aggarwal, C., Chang, Y., Liu, H.: Signed network embedding in social media. In: SIAM, pp. 327–335 (2017)Google Scholar
  13. 13.
    Wu, Z., Aggarwal, C.C., Sun, J.: The troll-trust model for ranking in signed networks. In: WSDM, pp. 447–456 (2016)Google Scholar
  14. 14.
    Yuan, S., Wu, X., Xiang, Y.: SNE: signed network embedding. In: Kim, J., Shim, K., Cao, L., Lee, J.-G., Lin, X., Moon, Y.-S. (eds.) PAKDD 2017. LNCS (LNAI), vol. 10235, pp. 183–195. Springer, Cham (2017). Scholar
  15. 15.
    Zheng, Q., Skillicorn, D.B.: Spectral embedding of signed networks. In: SIAM, pp. 55–63 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Ayan Kumar Bhowmick
    • 1
    Email author
  • Koushik Meneni
    • 1
  • Bivas Mitra
    • 1
  1. 1.Department of CSEIndian Institute of Technology KharagpurKharagpurIndia

Personalised recommendations