Exploiting Graph Invariants in Deep Learning
Lecture given by Marc Lelarge, researcher at INRIA and lecturer at Ecole Polytechnique and ENS-PSL as part of the next PRAIRIE colloquium.
Dr. Marc Lelarge is a researcher at INRIA. He is also a lecturer in deep learning at Ecole Polytechnique (Palaiseau, France) and Ecole Normale Superieure. He graduated from Ecole Polytechnique, qualified as an engineer at Ecole Nationale Superieure des Telecommunications (Paris) and received a PhD in Applied Mathematics from Ecole Polytechnique in 2005. Recipient of the 2012 SIGMETRICS rising star researcher award and the 2015 Best Publication in Applied Probability Award with Mohsen Bayati and Andrea Montanari for their work on compressed sensing.
Geometric deep learning is an attempt for geometric unification of a broad class of machine learning problems from the perspectives of symmetry and invariance. In this talk, I will present some advances of geometric deep learning applied to combinatorial structures. I will focus on various classes of graph neural networks that have been shown to be successful in a wide range of applications with graph structured data.
The Prairie Institute (PaRis AI Research InstitutE) is one of the four French Institutes of Artificial Intelligence, which were created as part of the national French initiative on AI announced by President Emmanuel Macron on May 29, 2018. After an open call for participation in July 2018 and two rounds of review by an international scientific committee, the Grenoble, Nice, Paris and Toulouse projects have officially received the 3IA certification on April 24, 2019.