WA3a.3

Seeking universal approximation for continuous limits of GNNs on large random graphs

Matthieu Cordonnier, Université Grenobles Alpes, France; Nicolas Keriven, CNRS, IRISA, France; Nicolas Tremblay, CNRS, Gipsa-lab, France; Samuel Vaiter, CNRS, LJAD, France
Session:
WA3a: Understanding Graph Neural Networks Lecture
Track:
Networks and Graphs
Location:
Scripps
Presentation Time:
Wed, 30 Oct, 09:05 - 09:30 PT (UTC -8)
Session Chair:
Luana Ruiz, Johns Hopkins University
Presentation
Discussion
Resources
No resources available.
Session WA3a
WA3a.1: Graph Signal Representations
José M. F. Moura, Carnegie Mellon University, United States
WA3a.2: Universal transferability for GNNs via graphons.
Mauricio Velasco, Universidad Catolica del Uruguay (UCU), Uruguay; Soledad Villar, Kaiying Xie, Johns Hopkins University (JHU), United States; Bernardo Rychtenberg, Universidad Catolica del Uruguay (UCU), United States
WA3a.3: Seeking universal approximation for continuous limits of GNNs on large random graphs
Matthieu Cordonnier, Université Grenobles Alpes, France; Nicolas Keriven, CNRS, IRISA, France; Nicolas Tremblay, CNRS, Gipsa-lab, France; Samuel Vaiter, CNRS, LJAD, France
WA3a.4: Generalization of Graph Neural Networks: Over Geometric Graphs Sampled from Manifolds
Zhiyang Wang, Juan Cervino, Alejandro Ribeiro, University of Pennsylvania, United States
Contacts