Machine learning domain adaptation in spin models with continuous phase transitions
- 2 September 2025
- journal article
- Published by American Physical Society (APS) in Physical Review E
- Vol. 112 (3) , 034104
Abstract
The main question raised in the article is whether a neural network trained on a spin lattice model in one universality class can be used to test a model in another universality class. The quantities of interest are the critical phase transition temperature and the correlation length exponent. In other words, the question of transfer learning is how "universal" the trained network is and under what conditions. For this purpose, we applied a supervised learning procedure to three two-dimensional models for which critical properties are precisely known: The Ising model, the four-state Potts model, and the Baxter-Wu model. We consider two datasets: One with spin configurations and one with binding energy configurations. We find that estimates of the critical temperature agree well with the known results for both datasets, but not with the results of cross-testing using the energy datasets of the two models: The four-state Potts model and the Ising model. Estimates of the critical length exponent are less regular, and appear to be more accurate for energy datasets. A good example is the cross-testing using the energy dataset between the Ising model and the Baxter-Wu model in both training and testing directions.Keywords
All Related Versions
Funding Information
- Russian Science Foundation (22-11-00259, 25-11-00158)
- National Research University Higher School of Economics
This publication has 30 references indexed in Scilit:
- Validity and Limitations of Supervised Learning for Phase Transition Research2023
- Machine-Learning Studies on Spin ModelsScientific Reports, 2020
- Machine learning phases of matterNature Physics, 2017
- A Guide to Monte Carlo Simulations in Statistical Physics2014
- Critical amplitude ratios of the Baxter–Wu modelNuclear Physics B, 2010
- Numerical revision of the universal amplitude ratios for the two-dimensional 4-state Potts modelNuclear Physics B, 2009
- Self-dual anisotropic two-dimensional Ising models with multispin interactionsJournal de Physique Lettres, 1982
- Ising Model on a Triangular Lattice with Three-spin Interactions. I. The Eigenvalue EquationAustralian Journal of Physics, 1974
- Some generalized order-disorder transformationsMathematical Proceedings of the Cambridge Philosophical Society, 1952
- Order-disorder in hexagonal latticesPhysica, 1950