A Knowledge-Based Semi-Supervised Crystal Property Prediction Framework With Consistency Regularization

doi:10.1109/TKDE.2026.3701591

A Knowledge-Based Semi-Supervised Crystal Property Prediction Framework With Consistency Regularization

2026-06-08

0

PRE

AI

DOI：10.1109/TKDE.2026.3701591

Original

Original request for help

Save

Abstract

En 中文

In the field of material science, the analysis of the properties of crystalline materials is of key importance. Recently, machine learning has become a prominent tool for predicting the properties of materials based on their structure. However, the application of machine learning to crystal property prediction faces two significant challenges. The first is the scarcity of labeled data, due to the time-consuming and resource-intensive process of crystal property labeling. The second is the importance of leveraging specialized knowledge when performing crystal structure analysis, which requires adapting machine learning methods specifically for the crystal domain. In this paper, we propose a new semi-supervised framework, a <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">K</b>nowledge-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">B</b>ased <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b>emi-<bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b>upervised crystal property prediction (KBSS) framework, which employs consistency regularization to leverage both labeled and unlabeled data while incorporating crystal knowledge guidance. Specifically, to use unlabeled data efficiently, the KBSS framework incorporates two key modules: a knowledge-guided augmentation (KGA) module and an adaptive pseudo-label filtering (APF) module. The KGA module utilizes the Monte Carlo method to leverage knowledge from the crystal domain to guide weak and strong augmentations of crystal structures. The APF module enhances the pseudo-labeling process for unlabeled crystal data by enabling task-guided uncertainty adjustment and category-aware pseudo-label selection. The experimental results show that KBSS achieves state-of-the-art performance.

Keywords:

Semi-supervised

consistency regularization

crystal property

knowledge-guided augmentation

A Knowledge-Based Semi-Supervised Crystal Property Prediction Framework With Consistency Regularization

Abstract

Journal

Organization