A Reinforcement Learning Approach to Gaining Social Capital with Partial Observation

  • He Zhao
  • Hongyi Su
  • Yang ChenEmail author
  • Jiamou Liu
  • Hong Zheng
  • Bo Yan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11670)


Social capital brings individuals benefits and advantages in societies. In this paper, we formalize two types of social capital: bonding capital refers to links to neighbours, while bridging capital refers to brokerages between others. We ask the questions: How would a marginal individual gain social capital with imperfect information of the society? We formalize this issue as the partially observable network building problem and propose two reinforcement learning algorithms: one guarantees the convergence to optimal values in theory, while the other is efficient in practice. We conduct simulations over a real-world dataset, and experimental results coincide with our theoretical analysis.


Social capital Network building Reinforcement learning 


  1. 1.
    Alaa, A.M., Ahuja, K., van der Schaar, M.: A micro-foundation of social capital in evolving social networks. IEEE Trans. Netw. Sci. Eng. 5(1), 14–31 (2018)CrossRefGoogle Scholar
  2. 2.
    Bourdieu, P.: The forms of capital. In: Handbook of Theory and Research for the Sociology of Education (1986)Google Scholar
  3. 3.
    Burt, R.S.: Structural holes and good ideas. Am. J. Sociol. 110(2), 349–399 (2004)CrossRefGoogle Scholar
  4. 4.
    Coleman, J.S.: Social capital in the creation of human capital. Am. J. Sociol. 94, S95–S120 (1988)CrossRefGoogle Scholar
  5. 5.
    Jackson, M.O.: A survey of network formation models: stability and efficiency. Group Formation Econ. Netw. Clubs Coalitions 664, 11–49 (2005)CrossRefGoogle Scholar
  6. 6.
    Moskvina, A., Liu, J.: How to build your network? A structural analysis. In: Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pp. 2597–2603. AAAI Press (2016)Google Scholar
  7. 7.
    Myers, D.: Relationship rewards. In: Social Psychology, pp. 392–439 (2010)Google Scholar
  8. 8.
    Page, L., Brin, S., Motwani, R., Winograd, T.: The pagerank citation ranking: bringing order to the web. Technical report, Stanford InfoLab (1999)Google Scholar
  9. 9.
    Rossi, R.A., Ahmed, N.K.: The network data repository with interactive graph analytics and visualization. In: Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (2015)Google Scholar
  10. 10.
    Tong, H., Faloutsos, C., Pan, J.Y.: Fast random walk with restart and its applications. In: Sixth International Conference on Data Mining, pp. 613–622. IEEE (2006)Google Scholar
  11. 11.
    Yan, B., Liu, Y., Liu, J., Cai, Y., Su, H., Zheng, H.: From the periphery to the center: information brokerage in an evolving network. In: Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, pp. 3912–3918. AAAI Press (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Beijing Lab of Intelligence Information Technology, School of Computer ScienceBeijing Institute of TechnologyBeijingChina
  2. 2.School of Computer ScienceThe University of AucklandAucklandNew Zealand

Personalised recommendations