Permutation-Aware Machine Learning Enables Data-Efficient Discovery of Single-Atom Catalysts
Jian-Hua Wang
Zheng-Da Chen
Xu Zhang
Meng-Xiao Han
Yu-Ping Sun
Zhong-Shi Liu
Xing Fan
Jian-Zhi Gao
Hai-Ping Lin
Abstract
Machine learning has emerged as a powerful strategy for accelerating catalyst discovery, yet its effectiveness in single-atom catalysts (SACs) is fundamentally constrained by the intrinsic small-data nature of coordinationdefined materials....