Ban lãnh đạo nghiên cứu : Patrick GALLINARI

Đồng hướng dẫn : LAMPRIER Sylvain

Apprentissage de la dynamique de propagation d'info dans les réseaux sociaux

In this thesis, we study information diffusion in online social networks. Websites like Facebook or Twitter have indeed become information medias, on which users create and share a lot of data. Most existing models of the information diffusion phenomenon relies on strong hypothesis about the structure and dynamics of diffusion. In this document, we study the problem of diffusion prediction in the context where the social graph is unknown and only user actions are observed.

• We propose a learning algorithm for the independant cascades model that does not take time into account. Experimental results show that this approach obtains better results than time-based learning schemes.
• We then propose several representations learning methods for this task of diffusion prediction. This let us define more compact and faster models.
• Finally, we apply our representation learning approach to the source detection task, where it obtains much better results than graph-based approaches.

Bài báo khoa học 2014-2017

• 2017
  • S. Bourigault, S. Lamprier, P. Gallinari : “Apprentissage de représentation pour la détection de source dans les réseaux sociaux”, COnférence en Recherche d'Informations et Applications - CORIA 2017, 14^th French Information Retrieval Conference, Marseille, France, pp. 235-250 (2017)
• 2016
  • S. Bourigault : “Apprentissage de la dynamique de propagation d’info dans les réseaux sociaux”, luận án, bảo vệ luận án 11/10/2016, ban lãnh đạo nghiên cứu Gallinari, Patrick, Đồng hướng dẫn : Lamprier, Sylvain (2016)
  • S. Bourigault, S. Lamprier, P. Gallinari : “Learning Distributed Representations of Users for Source Detection in Online Social Networks”, ECML PKDD 2016 - European Conference on Machine Learning and Knowledge Discovery in Databases, vol. 9852, Lecture Notes in Computer Science, Riva del Garda, Italy, pp. 265-281, (Springer) (2016)
  • S. Bourigault, S. Lamprier, P. Gallinari : “Apprentissage de Représentations Probabilistes pour la Prédiction de Diffusions d’Informations sur les Réseaux Sociaux”, COnférence en Recherche d'Information et Applications 2016 (CORIA), Toulouse, France, pp. 89-104 (2016)
  • S. Bourigault, S. Lamprier, P. Gallinari : “Representation Learning for Information Diffusion through Social Networks: an Embedded Cascade Model”, International Conference on Web Search and Data Mining, San Francisco, United States, pp. 573-582, (ACM) (2016)
  • S. Lamprier, S. Bourigault, P. Gallinari : “Influence learning for cascade diffusion models: focus on partial orders of infections”, Social Network Analysis and Mining, vol. 6 (1), pp. 93, (Springer) (2016)
• 2015
  • S. Lamprier, S. Bourigault, P. Gallinari : “Extracting Diffusion Channels from Real-World Social Data: a Delay-Agnostic Learning of Transmission Probabilities”, International Conference on Advances in Social Networks Analysis and Mining 2015, Paris, France (2015)
• 2014
  • S. Bourigault, C. Lagnier, S. Lamprier, L. Denoyer, P. Gallinari : “Apprentissage de représentation pour la diffusion d’Information dans les réseaux sociaux”, COnférence en Recherche d'Information et Applications 2014, CORIA 2014, Nancy, France, pp. 155-170 (2014)
  • S. Bourigault, C. Lagnier, S. Lamprier, L. Denoyer, P. Gallinari : “Learning social network embeddings for predicting information diffusion”, Proceedings of the 7^th ACM international conference on Web search and data mining, New York, United States, pp. 393-402, (ACM) (2014)
  • C. Lagnier, S. Bourigault, S. Lamprier, L. Denoyer, P. Gallinari : “Learning Information Spread in Content Networks”, ICLR 2014 - International Conference on Learning Representations, CoRR, Banff, Canada, pp. abs/1312.6169 (2014)