S³GNN mitigates oversquashing in message-passing networks via lightweight global mixing without strong prior assumptions, yielding up to 10x error reduction and 50% fewer parameters across multiple domains.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
Linearized Graph Sequence Models recast graph message-passing as sequence modeling via separation of processing depth from propagation depth to integrate modern sequence advances while preserving graph inductive bias.
Introduces Ramanujan Propagation as a graph rewiring method for GNNs that leverages Ramanujan graphs to ensure non-negative resistance curvature while preserving local connectivity and outperforming prior rewiring techniques.
This perspective article develops a definition of foundational MLIPs and poses six open questions that the authors believe will define future research in machine-learned interatomic potentials.
citing papers explorer
-
S$^3$GNN: Efficient Global Mixing and Local Message Passing for Long-Range Graph Learning
S³GNN mitigates oversquashing in message-passing networks via lightweight global mixing without strong prior assumptions, yielding up to 10x error reduction and 50% fewer parameters across multiple domains.
-
From Message-Passing to Linearized Graph Sequence Models
Linearized Graph Sequence Models recast graph message-passing as sequence modeling via separation of processing depth from propagation depth to integrate modern sequence advances while preserving graph inductive bias.
-
Ramanujan Graph Rewiring with Non Negative Resistance Curvature
Introduces Ramanujan Propagation as a graph rewiring method for GNNs that leverages Ramanujan graphs to ensure non-negative resistance curvature while preserving local connectivity and outperforming prior rewiring techniques.
-
Six Open Questions in Machine-Learned Interatomic Potential Foundation Models
This perspective article develops a definition of foundational MLIPs and poses six open questions that the authors believe will define future research in machine-learned interatomic potentials.