Classification with Graph-Based Methods

Résumé : Graphs, concise representations of relationships between entities, are widely used in various fields such as vision, chemistry, and biology. This talk focuses on using graph neural networks for supervised classification of signals sharing a common graph structure. We will evaluate the performance of these networks in two application domains: molecular biology, where the graph integrates information on gene co-expression, and neuroimaging, where the graph represents neuronal connections between brain regions. Despite their potential, graph neural networks’ performance is not yet optimal. We will discuss current limitations and opportunities for improving these networks.