cs.LGNov 7, 2026

Universal Approximation by Equivariant Message-Passing Graph Neural Networks with a Bilinear Readout

Authors: Pingbing Ming, Han Wang

Organizations: SKLMS, Institute of Computational Mathematics and Scientific/Engineering Computing, AMSS, Chinese Academy of Sciences, No. 55, East Road Zhong-Guan-Cun, Beijing 100190, China · National Key Laboratory of Computational Physics, Institute of Applied Physics and Computational Mathematics, Fenghao East Road 2, Beijing 100094, P.R. China, and HEDPS, CAPT, College of Engineering, Peking University, Beijing 100871, P.R. China

Abstract

We prove universal approximation for the bilinear-readout equivariant message-passing network (BREMP), a reference architecture for equivariant graph neural network interatomic potentials. Its layers combine equivariant convolutions with affine maps, and its readout forms invariants from products of the equivariant features. We construct a one-layer feature that determines the local environment up to permutations of atoms of the same type. The construction uses spherical harmonic filters of degree no larger than the largest number of neighbors at a common distance from the center. Iterating the construction recovers the environment reachable in as many hops as there are layers, using the same bound on filter degrees at the layer cutoff. The readout approximates every continuous invariant function of the features uniformly on compact sets. Together these give universal approximation of atomic energies at a prescribed physical range using a shorter layer cutoff. We assume that, throughout the admissible class, message passing reaches all neighbors in each physical environment within a common number of layers. Finally, DPA4, an interatomic potential architecture in production use, inherits this result by approximating the BREMP layers constructed in the proof and realizing the bilinear readout.

Figures & tables

Explore similar work

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

    Sep 1, 2026Pingbing Ming, Han WangMachine Learning Interatomic PotentialsGNN Expressivity

  2. NEMORA: Neural Equivariant Multipole Operators for Long-Range Atomistic Learning

    Oct 7, 2026Jay L. Kaplan, Samuel Varner, Rebecca Willett +1Machine Learning Interatomic PotentialsEquivariant GNNs

  3. Universal and efficient graph neural networks with dynamic attention for machine learning interatomic potentials

    Mar 24, 2026Shuyu Bi, Zhede Zhao, Qiangchao Sun +3Machine Learning Interatomic PotentialsGraph Neural Networks