In many problems in science and engineering, we are given access to data in the form of pairwise relationships between a set of n objects. These pairwise relationships naturally lead to an underlying graph, with nodes corresponding to the objects, and edges encoding the pairs of objects for which information is available. The goal, then, is to learn an underlying latent structure associated with the objects using the available pairwise data. Such problems arise in a wide range of applications, such as computer vision, recommendation systems, sports tournaments, biology, social sciences, to name a few. In many cases, the data is high dimensional with n of the order of thousands, or even millions (e.g. social networks), thus rendering the algorithmic task challenging from a practical point of view. The past decade has witnessed an impressive array of results – both from a theoretical and practical perspective – with several foundational results, as well as recent breakthroughs achieved by Graph Neural Networks in many important applications. 

This workshop will cover topics under the scope of such learning problems on large scale networks, including topics such as clustering, ranking, graph matching, graph neural networks, graph signal processing and dynamic processes on networks. It will feature a combination of long talks (1 hour each, by invited speakers), and contributed talks (20 mins each, by PhD students/post-docs/young researchers). The talks will include a general introduction to make them accessible to a wider audience.




Christophe Biernacki (Inria Lille, University of Lille)

Hemant Tyagi (Inria Lille)

Date and Place

Inria Lille - Nord Europe (Plenary Room, Building A) during 9-10 March 2023


  • [14/12/2022] Deadline for contributed talks extended to 15th January 2023!
  • [17/01/2023] Deadline for contributed talks further extended to 23rd January 2023...
  • [26/01/2023] We are still accepting submissions for contributed talks (till 1st February 2023)
  • [22/02/2023] Note: The workshop will now be held at Building A (plenary room) instead of Building B.
  • [27/02/2023] Registration possible till 1st March. 

Important dates

  • 1st November 2022 - 23rd January 2023: Submission of 1 page abstracts (Latex typeset pdf format) for contributed talks. The duration of each such talk will be 20 mins.
  • 25th January 2023: Notification for acceptance of contributed talks
  • 7th January 2023 - 15th February 2023: Registration for participants (this is free but mandatory, including for speakers!)

Invited speakers

  • Pierre Borgnat (CNRS, ENS Lyon)
  • Stephane Chretien (Univ. Lyon 2) 
  • Julien Hendrickx (UCLouvain)
  • Marc Lelarge (Inria and ENS Paris)
  • Pietro Liò (University of Cambridge)
  • Catherine Matias (CNRS, Sorbonne Université)
Online user: 1 Privacy