Graph Neural Network Approach to Predicting Magnetization in Quasi-One-Dimensional Ising Systems
This enables efficient magnetization prediction for physicists studying spin systems, but it is incremental as it applies an existing GNN method to a new domain.
The researchers tackled predicting magnetization in quasi-one-dimensional Ising systems by developing a graph neural network framework trained on Monte Carlo data, which accurately reproduced magnetization curves including plateaus and critical transitions.
We present a graph-based deep learning framework for predicting the magnetic properties of quasi-one-dimensional Ising spin systems. The lattice geometry is encoded as a graph and processed by a graph neural network (GNN) followed by fully connected layers. The model is trained on Monte Carlo simulation data and accurately reproduces key features of the magnetization curve, including plateaus, critical transition points, and the effects of geometric frustration. It captures both local motifs and global symmetries, demonstrating that GNNs can infer magnetic behavior directly from structural connectivity. The proposed approach enables efficient prediction of magnetization without the need for additional Monte Carlo simulations.