2 papers
cs.LG2026
LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN
Killian Cressant, Pedro B. Velloso
Graph Neural Networks (GNNs) suffer from two fundamental limitations: over-smoothing, where node representations become indistinguishable with depth, and over-squashing, where long…
stat.ML2026
Including Node Textual Metadata in Laplacian-constrained Gaussian Graphical Models
Jianhua Wang, Killian Cressant, Pedro Braconnot Velloso +1
This paper addresses graph learning in Gaussian Graphical Models (GGMs). In this context, data matrices often come with auxiliary metadata (e.g., textual descriptions associated wi…