Study of phase transition of Potts model with Domain Adversarial Neural Network

TL;DR

This paper introduces a transfer learning approach using Domain Adversarial Neural Networks to efficiently identify critical points and phase transition types in the 2D Potts model, achieving high accuracy with less data.

Contribution

The study applies DANN to phase transition analysis, enabling automatic critical point detection and phase transition classification with improved accuracy and reduced data requirements.

Findings

Accurately identifies critical points for q=3,4,5,7,10.

Determines phase transition order (first or second) simultaneously.

Calculates critical exponent ν for q=3 using data collapse.

Abstract

A transfer learning method, Domain Adversarial Neural Network (DANN), is introduced to study the phase transition of two-dimensional q-state Potts model. With the DANN, we only need to choose a few labeled configurations automatically as input data, then the critical points can be obtained after training the algorithm. By an additional iterative process, the critical points can be captured to comparable accuracy to Monte Carlo simulations as we demonstrate it for q = 3, 4, 5, 7 and 10. The type of phase transition (first or second-order) is also determined at the same time. Meanwhile, for the second-order phase transition at q=3, we can calculate the critical exponent $\nu$ by data collapse. Furthermore, compared to the traditional supervised learning, we found the DANN to be more accurate with lower cost.