Pairing-based graph neural network for simulating quantum materials

TL;DR

This paper introduces a pairing-based graph neural network that enhances quantum many-body system simulations by combining physical wavefunction models with neural network flexibility, achieving accurate results on complex electron-hole phases.

Contribution

The paper presents a novel neural network architecture that integrates BCS-type wavefunctions with graph neural networks for scalable quantum material simulations.

Findings

Accurate simulation of various interaction-induced phases.

Effective modeling of exciton condensates and Wigner crystals.

Demonstrates potential of neural network wavefunctions in quantum physics.

Abstract

We develop a pairing-based graph neural network for simulating quantum many-body systems. Our architecture augments a BCS-type geminal wavefunction with a generalized pair amplitude parameterized by a graph neural network. Variational Monte Carlo with our neural network simultaneously provides an accurate, flexible, and scalable method for simulating many-electron systems. We apply this method to two-dimensional semiconductor electron-hole bilayers and obtain accurate results on a variety of interaction-induced phases, including the exciton Bose-Einstein condensate, electron-hole superconductor, and bilayer Wigner crystal. Our study demonstrates the potential of physically-motivated neural network wavefunctions for quantum materials simulations.