2 citations · 4 across the 4 of their papers we have counts for
4 papers · 1 filter
Local Evidence and Geometric Readout Repair in Trained GNNs
Nadi Tomeh, Hugo Attali
Many node-classification GNNs apply a linear classifier to a nonnegative mixture of local messages. An error can reflect either poor mixture weights or a reachable logit set poorly…
Fast and Accurate Quotation Attribution in Literary Texts
Gaspard Michel, Hugo Attali, Elena V. Epure
Attributing quotations to their speakers in literary texts remains an open challenge. Standard methods, which independently predict a speaker mention for each quotation, are effici…
Ramanujan Graph Rewiring with Non Negative Resistance Curvature
Hugo Attali, Rachid El Jouhri
Graph Neural Networks (GNNs) have emerged as a powerful paradigm for learning on graph-structured data by iteratively propagating and aggregating information across edges. However,…
Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey
Hugo Attali, Nathalie Pernelle, Davide Buscaldi +1
Graph Neural Networks are powerful models for learning from graph-structured data, yet their effectiveness is often limited by two critical challenges: over-squashing, where inform…