Workshop on Graph Learning

A workshop on Graph Learning will be held at LINCS on May 14th, 2018.

The objective of this workshop is to bring together people from industry and academia for presenting and discussing the most recent learning techniques based on graphs, from both theoretical and practical perspectives.

The workshop will cover the following aspects:

  • Graph clustering
  • Topic detection
  • Recommender systems
  • Graph-based classification
  • Link prediction
  • Graph alignment
  • Social networks
  • Dynamic graphs
  • Graph signal processing
  • Speakers

    Oana Balalau (Max-Planck Institute)
    Alexis Benichoux (Deezer)
    Pierre Borgnat (ENS Lyon)
    Stephan Clémençon (Telecom ParisTech)
    Vincent Cohen-Addad (CNRS / UPMC)
    Matthias Grossglauser (EPFL)
    Alexandre Hollocou (Inria)
    Hervé Jegou (Facebook)
    Renaud Lambiotte (University of Oxford)
    Matthieu Latapy (CNRS / UPMC)
    Dimitrios Milioris (Nokia Bell Labs)
    Eric Siboni (Shift Technologies)
    Michal Valko (Inria)

    Tentative schedule

    9h – 10h30

  • Multimodal graph clustering for music recommendation
    Alexis Benichoux (Deezer)
  • Analysis of temporal interactions with link streams
    Matthieu Lattapy (CNRS / UPMC)
  • On the Performance of a Canonical Labeling for Matching Correlated Erdos-Rényi Graphs
    Matthias Grossglauser (EPFL)
  • 11h – 12h30

  • Insurance claims management and fraud detection
    Eric Siboni (Shift Technologies)
  • The many facets of community detection
    Renaud Lambiotte (University of Oxford)
  • Modularity for soft graph clustering
    Alexandre Hollocou (Inria)
  • 13h30 – 15h30

  • Building and exploiting large graphs connecting images
    Hervé Jegou (Facebook)
  • Directed graph signal processing with application to learning and forecast
    Pierre Borgnat (ENS Lyon)
  • On graph reconstruction via empirical risk minimization
    Stephan Clémençon (Telecom ParisTech)
  • Hierarchical clustering: Objective functions and algorithms
    Vincent Cohen-Addad (CNRS / UPMC)
  • 16h – 17h30

  • On finding dense subgraphs and events in social media
    Oana Balalau (Max-Planck Institute)
  • Topic detection and classification in Twitter
    Dimitrios Milioris (Nokia Bell Labs)
  • Online influence maximization
    Michal Valko (Inria)
  • Organizers

    Thomas Bonald (Telecom ParisTech)
    Marc Lelarge (Inria)
    Laurent Massoulié (Inria / Microsoft)