Skip to content

Author

Pietro Liò

2 papers indexed here

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.

#machine learning Preprint Oct 2026

Diagnosing GNN Failure Modes with Layer-Wise Probe Entropy

It is shown that the onset of entropy degradation separates the two main GNN failure modes: structural mismatch under heterophily, which appears from the earliest layers even in shallow models, and excessive-depth oversmoothing, which emerges only as propagation depth increases.

Shan Bao, M. Catala, Pietro Liò · 0 citations
#machine learning Preprint Oct 2026

Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashing

This work introduces TRIP and its generalisation GRIP and its generalisation GRIP, constructive procedures that turn any graph into a provably long-ranged task by drawing features from stable distributions, and formally proves that violating any one of them admits failure modes that undermine conclusions drawn from the...

Ferran Hernandez Caralt, Simon Heilig, A. Bazaga et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.