Soft Contrastive Learning for Unsupervised Discovery of Phases of Matter
Abstract
A machine learning (ML) framework for phase-diagram construction in condensed matter systems with unknown phase structure is presented. The method combines physically motivated descriptors with contrastive representation learning and a two-stage data-generation workflow. First, a sparse set of configurations is generated by Monte Carlo simulated annealing in order to train a contrastive neural network that produces a low-dimensional embedding. Consequently, representative phase configurations are used as initial conditions for gradient-based optimization on a dense parameter grid, enabling efficient generation of refined datasets for high-resolution phase-diagram construction. In order to optimize the workflow, a variant of the method, in which derived descriptors are used as soft labels in the contrastive objective, is examined as well. The framework is demonstrated on a PbZrO3-inspired model potential formulated in terms of coupled order-parameter fields and used as a physically motivated testbed for exploring configuration diversity and phase behavior. The proposed approach provides a physically informed route to ML-assisted phase-diagram construction that integrates data analysis with adaptive dataset refinement.
Related
- Unsupervised and probabilistic learning with Contrastive Local Learning Networks: The Restricted Kirchhoff Machine
- QuantumMatterExplorer: An Autonomous Agent for the Discovery of Quantum Many-Body Phases of Matter
- Classification of topological phases of matter in stochastic systems
- Lifting the mixed to the pure: quantum phases of matter from canonical purification
- Floquet physics from quantized light-matter interaction: geometric phases, gauge consistency, and entanglement
BibTeX
@misc{benes2026soft,
title = {{Soft Contrastive Learning for Unsupervised Discovery of Phases of Matter}},
author = {Vít Beneš and Pavel Baláž and Dmytro Bohdanov and Jiří Hlinka},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.08116},
eprint = {2610.08116},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.08116},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Soft Contrastive Learning for Unsupervised Discovery of Phases of Matter
AU - Vít Beneš
AU - Pavel Baláž
AU - Dmytro Bohdanov
AU - Jiří Hlinka
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2610.08116
UR - https://arxiv.org/abs/2610.08116
AB - A machine learning (ML) framework for phase-diagram construction in condensed matter systems with unknown phase structure is presented. The method combines physically motivated descriptors with contrastive representation learning and a two-stage data-generation workflow. First, a sparse set of configurations is generated by Monte Carlo simulated annealing in order to train a contrastive neural network that produces a low-dimensional embedding. Consequently, representative phase configurations are used as initial conditions for gradient-based optimization on a dense parameter grid, enabling efficient generation of refined datasets for high-resolution phase-diagram construction. In order to optimize the workflow, a variant of the method, in which derived descriptors are used as soft labels in the contrastive objective, is examined as well. The framework is demonstrated on a PbZrO3-inspired model potential formulated in terms of coupled order-parameter fields and used as a physically motivated testbed for exploring configuration diversity and phase behavior. The proposed approach provides a physically informed route to ML-assisted phase-diagram construction that integrates data analysis with adaptive dataset refinement.
ER -