科研速览 · Science Skim继续刷下去 · Keep skimming →
◇ arXiv2026-09-01· cs.LG

Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials

Pingbing Ming, Han Wang

原始摘要(英文原文)· Original abstract
We prove that the Hypergraph Neural Network, an invariant architecture with 3-body message passing, is a universal approximator for potential energy surfaces. Our main contribution is a multi-layer completeness theory. We show that $L$ layers of message passing on sparse, cutoff-based graphs achieve the same representational power as having access to the full $L$-hop neighborhood, provided the configurations are generic, satisfy an overlap condition and a connectivity condition. This provides the first rigorous justification for the common practice of using multi-layer message passing with a per-layer cutoff smaller than the physical interaction range, the setting used by virtually all practical graph neural network based machine-learned interatomic potentials. As immediate consequences, we show that both DPA3 and CHGNet architectures inherit universal approximation.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

Why Multi-Layer Message Passing Works: Completeness Theory for Graph Neural Network Interatomic Potentials — 科研速览 Science Skim