.png){kind=icon}
.png){kind=icon}
Return
MatSub: A Performance-Oriented Subgroup Discovery Framework for Materials Informatics
.png){kind=icon}
PRE
AI
DOI：10.1016/j.cpc.2026.110189.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Developed open-source SGD software tailored for materials informatics • Introduced quality functions targeting performance relevance over statistical exceptionality • Implemented orthogonal subgroup search to capture multiple mechanisms • Applied to SAACs segregation energies to extract interpretable design rules • Enables alternative-mechanism analysis beyond global machine learning models
Keywords:
Subgroup discovery
Materials informatics
Machine learning
Design rules
Orthogonal search
Journal
IF:
3.4
Papers:
1.2W
Citations:
3.7W