Author

Killian Cressant

h-index 1 View on Semantic Scholar

We have 1 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

LEED: Local Embedding Evolution Distance for over-smoothing estimation and virtual node selection in GNN

This paper proposes LEED (Local Embedding Evolution Distance), a novel local metric that quantifies over-smoothing by tracking the evolution of individual node embeddings across layers, and uses LEED as a unique criterion to guide the construction of Local Virtual Nodes to mitigate over-squashing.

Killian Cressant, P. B. Velloso · 0 citations