Effect of Network Topology on Neighbourhood-Aided Collective Learning

  • Lise-Marie Veillon
  • Gauvain Bourgne
  • Henry Soldano
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10448)


This article is about multi-agent collective learning in networks. An agent revises its current model when collecting a new observation inconsistent with it. While revising, the agent interacts with its neighbours in the community, and benefits from observations that other agents send on a utility basis. When considering the learning speed of an agent with respect to all the observations within the community, it clearly depends on the neighbourhood structure, i.e. on the network topology. A comprehensive experimental study characterizes this influence, showing the main factors that affect neighbourhood-aided collective learning. Two kinds of informations are propagated in the networks: hypotheses and counter-examples. This study also weights the impact of these propagation by considering some variants in which one kind of propagation is stopped. Our main purpose is to understand how network characteristics affect to what extent the agents learn and share models and observations, and consequently the learning speed within the community.


Collective learning Multi-agents learning Agents network 


  1. 1.
    Angluin, D.: Queries revisited. Theor. Comput. Sci. 313(2), 175–194 (2004)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Bourgne, G., Bouthinon, D., El Fallah Seghrouchni, A., Soldano, H.: Collaborative concept learning: non individualistic vs individualistic agents. In: IEEE International Conference on Tools with Artificial Intelligence (ICTAI), pp. 653–657. IEEE Computer Society, Newark, USA, November 2009Google Scholar
  3. 3.
    Bourgne, G., El Fallah Seghrouchni, A., Soldano, H.: Smile: sound multi-agent incremental learning;-). In: International Conference on Autonomous Agents and Multiagent Systems (AAMAS), pp. 164–171. ACM, Honolulu, Hawaï (2007)Google Scholar
  4. 4.
    Bourgne, G., El Fallah Seghrouchni, A., Soldano, H.: Learning in a fixed or evolving network of agents. In: ACM-IAT 2009. IEEE (2009)Google Scholar
  5. 5.
    Bourgne, G., Soldano, H., El Fallah Seghrouchni, A.: Learning better together. In: Coelho, H., Studer, R., Wooldridge, M. (eds.) ECAI. Frontiers in Artificial Intelligence and Applications, vol. 215, pp. 85–90. IOS Press, The Netherlands (2010)Google Scholar
  6. 6.
    Guille, A., Hacid, H., Favre, C., Zighed, D.A.: Information diffusion in online social networks: a survey. SIGMOD Rec. 42(2), 17–28 (2013)CrossRefGoogle Scholar
  7. 7.
    Zollman, K.J.S.: Network Epistemology. Ph.D. thesis, University of California, Irvine (2007)Google Scholar
  8. 8.
    Ontañón, S., Plaza, E.: Multiagent inductive learning: an argumentation-based approach. In: Proceedings of ICML 2010, pp. 839–846. Omnipress (2010)Google Scholar
  9. 9.
    Watts, D.J., Strogatz, S.H.: Collective dynamics of /‘small-world/’ networks. Nature 393(6684), 440–442 (1998)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Lise-Marie Veillon
    • 1
  • Gauvain Bourgne
    • 2
  • Henry Soldano
    • 1
    • 3
  1. 1.Université Paris 13, Sorbonne Paris Cité, L.I.P.N UMR-CNRS 7030VilletaneuseFrance
  2. 2.CNRS & Sorbonne Universités, UPMC Université Paris 06, LIP6 UMR 7606ParisFrance
  3. 3.Atelier de BioInformatique, ISYEB - UMR 7205 CNRS MNHN UPMC EPHE, Museum National D’Histoire NaturelleParisFrance

Personalised recommendations