MOF-KAN: Kolmogorov–Arnold Networks for Digital Discovery of Metal–Organic Frameworks DOI
Xiaoyu Wu,

Xianyu Song,

Yifei Yue

et al.

The Journal of Physical Chemistry Letters, Journal Year: 2025, Volume and Issue: unknown, P. 2452 - 2459

Published: Feb. 27, 2025

Digital discovery of functional materials, such as metal–organic frameworks (MOFs), entails accurate and data-efficient approaches to navigate complex chemical structural space. Based on an innovative deep learning approach, namely, Kolmogorov–Arnold Networks (KANs), we introduce MOF-KAN, a state-of-the-art architecture the first application KANs digital MOFs. Through meticulous fine-tuning network architecture, demonstrate that MOF-KAN outperforms standard multilayer perceptrons (MLPs) in predicting diverse properties for MOFs, including gas separation, electronic band gap, thermal expansion. Furthermore, excels low-data regimes, facilitating robust performance challenging prediction scenarios. Feature importance analysis reveals accurately captures critical features MOFs relevant targeted properties. not only serves transformative tool rational design materials but also holds broad applicability across various domains physical sciences.

Language: Английский

MOF-KAN: Kolmogorov–Arnold Networks for Digital Discovery of Metal–Organic Frameworks DOI
Xiaoyu Wu,

Xianyu Song,

Yifei Yue

et al.

The Journal of Physical Chemistry Letters, Journal Year: 2025, Volume and Issue: unknown, P. 2452 - 2459

Published: Feb. 27, 2025

Digital discovery of functional materials, such as metal–organic frameworks (MOFs), entails accurate and data-efficient approaches to navigate complex chemical structural space. Based on an innovative deep learning approach, namely, Kolmogorov–Arnold Networks (KANs), we introduce MOF-KAN, a state-of-the-art architecture the first application KANs digital MOFs. Through meticulous fine-tuning network architecture, demonstrate that MOF-KAN outperforms standard multilayer perceptrons (MLPs) in predicting diverse properties for MOFs, including gas separation, electronic band gap, thermal expansion. Furthermore, excels low-data regimes, facilitating robust performance challenging prediction scenarios. Feature importance analysis reveals accurately captures critical features MOFs relevant targeted properties. not only serves transformative tool rational design materials but also holds broad applicability across various domains physical sciences.

Language: Английский

Citations

0