Fragkiskos Malliaros — accepted AI-conference papers

2026

Graph Rewiring in GNNs to Mitigate Over-Squashing and Over-Smoothing: A Survey

Hugo Attali, Nathalie Pernelle, Davide Buscaldi, Fragkiskos Malliaros

IJCAI 2026

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 information from distant nodes is excessively compressed, and over-smoothing, where repeated propagation makes node representa

Cited by 0 Scholar ↗

2026

TriForces: Augmenting Atomistic GNNs for Transferable Representations

Ali Ramlaoui, Alexandre Duval, Hannah Bull, Victor Schmidt, Hugues Talbot, Fragkiskos Malliaros +1

ICML 2026poster

Machine learning interatomic potentials (MLIPs) achieve excellent accuracy when trained on large Density Functional Theory (DFT) data. To be useful in practice, they must often be adapted to target chemistries using small and expensive task-specific datasets. However, MLIPs transfer inconsistently a…

Cited by 0 Source ↗Scholar ↗