4 papers
What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding
Nicolas Keriven, Samuel Vaiter
We aim to deepen the theoretical understanding of Graph Neural Networks (GNNs) on large graphs, with a focus on their expressive power. Existing analyses relate this notion to the…
Gradient scarcity with Bilevel Optimization for Graph Learning
Hashem Ghanem, Samuel Vaiter, Nicolas Keriven
A common issue in graph learning under the semi-supervised setting is referred to as gradient scarcity. That is, learning graphs by minimizing a loss on a subset of nodes causes ed…
Supervised learning of analysis-sparsity priors with automatic differentiation
Hashem Ghanem, Joseph Salmon, Nicolas Keriven +1
Sparsity priors are commonly used in denoising and image reconstruction. For analysis-type priors, a dictionary defines a representation of signals that is likely to be sparse. In…
Compressive K-means
Nicolas Keriven, Nicolas Tremblay, Yann Traonmilin +1
The Lloyd-Max algorithm is a classical approach to perform K-means clustering. Unfortunately, its cost becomes prohibitive as the training dataset grows large. We propose a compres…