no code implementations • 2 Mar 2023 • Jason Piquenot, Aldo Moscatelli, Maxime Bérar, Pierre Héroux, Romain Raveaux, Jean-Yves Ramel, Sébastien Adam
This paper introduces a framework for formally establishing a connection between a portion of an algebraic language and a Graph Neural Network (GNN).
2 code implementations • 8 Jun 2021 • Muhammet Balcilar, Pierre Héroux, Benoit Gaüzère, Pascal Vasseur, Sébastien Adam, Paul Honeine
Since the Message Passing (Graph) Neural Networks (MPNNs) have a linear complexity with respect to the number of nodes when applied to sparse graphs, they have been widely implemented and still raise a lot of interest even though their theoretical expressive power is limited to the first order Weisfeiler-Lehman test (1-WL).
1 code implementation • ICLR 2021 • Muhammet Balcilar, Guillaume Renton, Pierre Héroux, Benoit Gaüzère, Sébastien Adam, Paul Honeine
Since the graph isomorphism problem is NP-intermediate, and Weisfeiler-Lehman (WL) test can give sufficient but not enough evidence in polynomial time, the theoretical power of GNNs is usually evaluated by the equivalence of WL-test order, followed by an empirical analysis of the models on some reference inductive and transductive datasets.
no code implementations • 21 May 2015 • Julien Lerouge, Zeina Abu-Aisheh, Romain Raveaux, Pierre Héroux, Sébastien Adam
Moreover, a relaxation of the domain constraints in the formulations provides efficient lower bound approximations of the GED.