Interpretable and unsupervised phase classification

Abstract: Fully automated classification methods that provide direct physical insights into phase diagrams are of current interest. Interpretable, i.e., fully explainable, methods are desired for which we understand why they yield a given phase classification. Ideally, phase classification methods should also be unsupervised. That is, they should not require prior labeling or knowledge of the phases of matter to be characterized. Here, we demonstrate an unsupervised machine-learning method for phase classification, which is rendered interpretable via an analytical derivation of the functional relationship between its optimal predictions and the input data. Based on these findings, we propose and apply an alternative, physically-motivated, data-driven scheme, which relies on the difference between mean input features. This mean-based method does not rely on any predictive model and is thus computationally cheap and directly explainable. As an example, we consider the physically rich ground-state phase diagram of the spinless Falicov-Kimball model

Object Details

• Location: Deutsche Nationalbibliothek Frankfurt am Main
• Extent: Online-Ressource
• Language: Englisch
• Notes: Physical review research. - 3, 3 (2021) , 033052, ISSN: 2643-1564

Contributors, Places and Time

• Event: Veröffentlichung
• (where): Freiburg
• (who): Universität
• (when): 2024
• Creator: Arnold, Julian ; Schäfer, Frank ; Žonda, Martin ; Lode, Axel U. J.

Further information

• DOI: 10.1103/physrevresearch.3.033052
• URN: urn:nbn:de:bsz:25-freidok-2479147
• Rights: Open Access; Der Zugriff auf das Objekt ist unbeschränkt möglich.
• Last update: 14.08.2025, 10:56 AM CEST