English
Related papers

Related papers: Beyond Independent Error Assumptions in Large GNN …

200 papers

For reliability, it is important that the predictions made by machine learning methods are interpretable by human. In general, deep neural networks (DNNs) can provide accurate predictions, although it is difficult to interpret why such…

Machine Learning · Computer Science 2021-12-16 Yuya Yoshikawa , Tomoharu Iwata

To date, density functional theory (DFT) is one of the most accurate and yet practical theory to gain insight about materials properties. Although successful, the computational cost is the main hurdle even today. A way out is combining DFT…

Materials Science · Physics 2019-04-19 Shweta Mehta , Sheena Agarwal , Kavita Joshi

Deep-learning density functional theory (DFT) shows great promise to significantly accelerate material discovery and potentially revolutionize materials research. However, current research in this field primarily relies on data-driven…

Computational Physics · Physics 2024-08-14 Yang Li , Zechen Tang , Zezhou Chen , Minghui Sun , Boheng Zhao , He Li , Honggeng Tao , Zilong Yuan , Wenhui Duan , Yong Xu

Standard forms of density-functional theory (DFT) have good predictive power for many materials, but are not yet fully satisfactory for solid, liquid and cluster forms of water. We use a many-body separation of the total energy into its…

Materials Science · Physics 2013-03-05 M. J. Gillan , D. Alfè , A. P. Bartók , G. Csányi

In recent years Deep Neural Networks (DNNs) have been rapidly developed in various applications, together with increasingly complex architectures. The performance gain of these DNNs generally comes with high computational costs and large…

Machine Learning · Computer Science 2017-12-05 Yiren Zhou , Seyed-Mohsen Moosavi-Dezfooli , Ngai-Man Cheung , Pascal Frossard

The calculation of the band-gap by density-functional theory (DFT) methods is examined by considering the behavior of the energy as a function of number of electrons. It is found that the incorrect band-gap prediction with most approximate…

Materials Science · Physics 2009-11-13 Aron J. Cohen , Paula Mori-Sánchez , Weitao Yang

Predictions of observable properties by density-functional theory calculations (DFT) are used increasingly often in experimental condensed-matter physics and materials engineering as data. These predictions are used to analyze recent…

Materials Science · Physics 2015-03-20 Kurt Lejaeghere , Veronique Van Speybroeck , Guido Van Oost , Stefaan Cottenier

This study benchmarks the GFN family of semiempirical methods (GFN1-xTB, GFN2-xTB, GFN0-xTB, and GFN-FF) against density functional theory (DFT) for the evaluation of optimized molecular geometries and electronic properties of small organic…

With recent advancements in graph neural networks (GNNs), spectral GNNs have received increasing popularity by virtue of their ability to retrieve graph signals in the spectral domain. These models feature uniqueness in efficient…

Machine Learning · Computer Science 2025-08-21 Ningyi Liao , Haoyu Liu , Zulun Zhu , Siqiang Luo , Laks V. S. Lakshmanan

In approximate density functional theory (DFT), the self-interaction error is an electron delocalization anomaly associated with underestimated insulating gaps. It exhibits a predominantly quadratic energy-density curve that is amenable to…

Chemical Physics · Physics 2016-12-21 Glenn Moynihan , Gilberto Teobaldi , David D. O'Regan

Point defects play a central role in driving the properties of materials. First-principles methods are widely used to compute defect energetics and structures, including at scale for high-throughput defect databases. However, these methods…

Machine Learning · Computer Science 2025-09-30 Evan Dramko , Yihuang Xiong , Yizhi Zhu , Geoffroy Hautier , Thomas Reps , Christopher Jermaine , Anastasios Kyrillidis

This study reports grain boundary (GB) energy calculations for 46 symmetric-tilt GBs in alpha-iron using molecular mechanics based on an artificial neural network (ANN) potential and compares the results with calculations based on the…

We present an analytical theory for the gate electrostatics and the classical and quantum capacitance of the graphene nanoribbons (GNRs) and compare it with the exact self-consistent numerical calculations based on the tight-binding…

Mesoscale and Nanoscale Physics · Physics 2014-02-12 A. A. Shylau , J. W. Klos , I. V. Zozoulenko

Inferring transient molecular structural dynamics from diffraction data is an ambiguous task that often requires different approximation methods. In this paper we present an attempt to tackle this problem using machine learning. While most…

Chemical Physics · Physics 2023-08-09 Hazem Daoud , Dhruv Sirohi , Endri Mjeku , John Feng , Saeed Oghbaey , R. J. Dwayne Miller

Machine learning has emerged as a powerful tool for predicting molecular properties in chemical reaction networks with reduced computational cost. However, accurately predicting energies of transition state (TS) structures remains a…

Chemical Physics · Physics 2025-04-29 Stefan Gugler , Markus Reiher

Recent studies on Graph Neural Networks(GNNs) provide both empirical and theoretical evidence supporting their effectiveness in capturing structural patterns on both homophilic and certain heterophilic graphs. Notably, most real-world…

Machine Learning · Computer Science 2023-10-17 Haitao Mao , Zhikai Chen , Wei Jin , Haoyu Han , Yao Ma , Tong Zhao , Neil Shah , Jiliang Tang

Explainability of graph neural networks (GNNs) aims to answer "Why the GNN made a certain prediction?", which is crucial to interpret the model prediction. The feature attribution framework distributes a GNN's prediction to its input…

Machine Learning · Computer Science 2022-02-02 Ying-Xin Wu , Xiang Wang , An Zhang , Xia Hu , Fuli Feng , Xiangnan He , Tat-Seng Chua

Large-eddy simulations (LES) require closures for filtered production rates because the resolved fields do not contain all correlations that govern chemical source terms. We develop a graph neural network (GNN) that predicts filtered…

Fluid Dynamics · Physics 2026-03-23 Priyabrat Dash , Mathis Bode , Konduri Aditya

Most existing Graph Neural Networks (GNNs) are proposed without considering the selection bias in data, i.e., the inconsistent distribution between the training set with test set. In reality, the test data is not even available during the…

Machine Learning · Computer Science 2022-01-27 Shaohua Fan , Xiao Wang , Chuan Shi , Kun Kuang , Nian Liu , Bai Wang

In recent years, deep perceptual loss has been widely and successfully used to train machine learning models for many computer vision tasks, including image synthesis, segmentation, and autoencoding. Deep perceptual loss is a type of loss…

Computer Vision and Pattern Recognition · Computer Science 2024-07-04 Gustav Grund Pihlgren , Konstantina Nikolaidou , Prakash Chandra Chhipa , Nosheen Abid , Rajkumar Saini , Fredrik Sandin , Marcus Liwicki