Prediction Errors of Molecular Machine Learning Models Lower than Hybrid DFT Error.

By Felix A. Faber, Luke Hutchison, Bing Huang, Justin Gilmer, Sam Schoenholz, George E. Dahl, Oriol Vinyals, Steven M. Kearnes, Patrick Riley, O. V. Lilienfeld and 2 more. 2017

593 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Materials Chemistry, Physical and Theoretical Chemistry, Computational Chemistry & Drug Discovery, AI for Physical Sciences

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

1. Tess E. Smidt
2. Stephan Günnemann
3. Johannes Klicpera
4. Shyue Ping Ong
5. Chi Chen
6. Sam Schoenholz
7. Janek Groß
8. Olexandr Isayev

In Materials Chemistry

1. Tess E. Smidt
2. Shyue Ping Ong
3. Chi Chen
4. Stephan Günnemann
5. Johannes Klicpera
6. Sam Schoenholz
7. Ekin Dogus Cubuk
8. Anubhav Jain

In Physical and Theoretical Chemistry

1. Stephan Günnemann
2. Johannes Klicpera
3. Sam Schoenholz
4. Tess E. Smidt
5. Chi Chen
6. A. Pais
7. Adrian E. Roitberg
8. Christian Devereux

In Computational Chemistry & Drug Discovery

1. Tess E. Smidt
2. Stephan Günnemann
3. Johannes Klicpera
4. Shyue Ping Ong
5. Chi Chen
6. Janek Groß
7. Sam Schoenholz
8. Patrick F. Riley

In AI for Physical Sciences

1. Sam Schoenholz
2. Tess E. Smidt
3. Ekin Dogus Cubuk
4. Peter Bjørn Jørgensen
5. Karsten Wedel Jacobsen
6. Chi Chen
7. Aron Walsh
8. A. Pais

Citations in the corpus

• Directional Message Passing for Molecular Graphs (2020, background): “3 kcal mol − 1 for energy (Faber et al., 2017)), so any remaining difference to real-world data is almost exclusively due to errors in the DFT simulation.”
• Tensor Field Networks: Rotation- and Translation-Equivariant Neural Networks for 3D Point Clouds (2018, background): “Many of these use only the pairwise distance between atoms (e.g. SchNet [13] and the graph convolutional model from Faber et al. [14]).”
• Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials (2018, methodology): “The model was reimplemented by Faber et al. (2017) and Gilmer et al. (2017).”
• JAX, M.D.: End-to-End Differentiable, Hardware Accelerated, Molecular Dynamics in Pure Python (2019, background): “…and more accurate (Behler & Parrinello, 2007; Behler, 2011; Artrith et al., 2011; Artrith & Behler, 2012; Artrith et al., 2018; Deringer et al., 2018a; Bartók et al., 2018; Yao et al., 2018; Seko et al., 2015; Deringer et al., 2018b; Cubuk et al., 2017a; Faber et al., 2017; Gilmer et al., 2017).”
• Motif-based Graph Self-Supervised Learning for Molecular Property Prediction (2021, methodology): “more efficient solutions for molecular property prediction, various machine learning methods have been leveraged such as kernel ridge regression, random forest, and convolutional neural networks [6, 26, 36].”