no code implementations • 24 Jul 2023 • Stevan Stanovic, Benoit Gaüzère, Luc Brun

Convolutional Neural Networks (CNNs) have enabled major advances in image classification through convolution and pooling.

no code implementations • 2 Aug 2022 • Stevan Stanovic, Benoit Gaüzère, Luc Brun

Consequently, our method does not discard any vertex information nor artificially increase the density of the graph.

no code implementations • 29 Nov 2021 • Luc Brun, Benoit Gaüzère, Sébastien Bougleux, Florian Yger

Conversely, the remaining elements of V2 correspond to the image of the epsilon pseudo element of V1.

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 • 26 Jun 2019 • Nicolas Boria, S'ebastien Bougleux, Benoit Gaüzère, Luc Brun

Computing a graph prototype may constitute a core element for clustering or classification tasks.

1 code implementation • Pattern Recognition 2019 • Linlin Jia, Benoit Gaüzère, Paul Honeine

In this work, we propose a thorough investigation and comparison of graph kernels based on different linear patterns, namely walks and paths.

Ranked #36 on Graph Classification on MUTAG

Cannot find the paper you are looking for? You can
Submit a new open access paper.

Contact us on:
hello@paperswithcode.com
.
Papers With Code is a free resource with all data licensed under CC-BY-SA.