Metadynamics for training neural network model chemistries: A competitive assessment
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
Neural network model chemistries (NNMCs) promise to facilitate the accurate exploration of chemical space and simulation of large reactive systems. One important path to improving these models is to add layers of physical detail, especially long-range forces. At short range, however, these models are data driven and data limited. Little is systematically known about how data should be sampled, and “test data” chosen randomly from some sampling techniques can provide poor information about generality. If the sampling method is narrow, “test error” can appear encouragingly tiny while the model fails catastrophically elsewhere. In this manuscript, we competitively evaluate two common sampling methods: molecular dynamics (MD), normal-mode sampling, and one uncommon alternative, Metadynamics (MetaMD), for preparing training geometries. We show that MD is an inefficient sampling method in the sense that additional samples do not improve generality. We also show that MetaMD is easily implemented in any NNMC software package with cost that scales linearly with the number of atoms in a sample molecule. MetaMD is a black-box way to ensure samples always reach out to new regions of chemical space, while remaining relevant to chemistry near kbT. It is a cheap tool to address the issue of generalization.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Long-range corrected hybrid density functionals with damped atom–atom dispersion corrections
Chai, J.-D., & Head-Gordon, M. (2008) · Physical Chemistry Chemical Physics · doi:10.1039/b810189b · Cited by 14,648
Laio, A., & Parrinello, M. (2002) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.202427399 · Cited by 5,626
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
Behler, J., & Parrinello, M. (2007) · Physical Review Letters · doi:10.1103/physrevlett.98.146401 · Cited by 5,010
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015) · arXiv · doi:10.48550/arxiv.1511.07289 · Cited by 4,513
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
Rupp, M., Tkatchenko, A., Müller, K.-R., & von Lilienfeld, O. A. (2012) · Physical Review Letters · doi:10.1103/physrevlett.108.058301 · Cited by 2,312
Quantum chemistry structures and properties of 134 kilo molecules
Ramakrishnan, R., Dral, P. O., Rupp, M., & von Lilienfeld, O. A. (2014) · Scientific Data · doi:10.1038/sdata.2014.22 · Cited by 1,966 · cited 1×
“We urge caution against a culture of testing NNMCs on benchmark datasets following the tradition of quantum chemistry 12,71–75 especially datasets near equilibrium.”
BackgroundANI-1: an extensible neural network potential with DFT accuracy at force field computational cost
Smith, J. S., Isayev, O., & Roitberg, A. E. (2017) · Chemical Science · doi:10.1039/c6sc05720a · Cited by 1,921
Quantum-chemical insights from deep tensor neural networks
Schütt, K. T., Arbabzadah, F., Chmiela, S., Müller, K. R., & Tkatchenko, A. (2017) · Nature Communications · doi:10.1038/ncomms13890 · Cited by 1,445
Constructing high‐dimensional neural network potentials: A tutorial review
Behler, J. (2015) · International Journal of Quantum Chemistry · doi:10.1002/qua.24890 · Cited by 884
Hansen, K., Biegler, F., Ramakrishnan, R., Pronobis, W., von Lilienfeld, O. A., Müller, K.-R., & Tkatchenko, A. (2015) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.5b00831 · Cited by 815
Cited by
Unke, O. T., Chmiela, S., Sauceda, H. E., Gastegger, M., Poltavsky, I., Schütt, K. T., Tkatchenko, A., & Müller, K.-R. (2021) · Chemical Reviews · doi:10.1021/acs.chemrev.0c01111 · Cited by 1,647
From DFT to machine learning: recent approaches to materials science–a review
Schleder, G. R., Padilha, A. C. M., Acosta, C. M., Costa, M., & Fazzio, A. (2019) · Journal of Physics: Materials · doi:10.1088/2515-7639/ab084b · Cited by 852
Less is more: Sampling chemical space with active learning
Smith, J. S., Nebgen, B., Lubbers, N., Isayev, O., & Roitberg, A. E. (2018) · The Journal of Chemical Physics · doi:10.1063/1.5023802 · Cited by 811
Active learning of uniformly accurate interatomic potentials for materials simulation
Zhang, L., Lin, D.-Y., Wang, H., Car, R., & E, W. (2019) · Physical Review Materials · doi:10.1103/physrevmaterials.3.023804 · Cited by 521
Machine Learning for Electronically Excited States of Molecules
Westermayr, J., & Marquetand, P. (2021) · Chemical Reviews · doi:10.1021/acs.chemrev.0c00749 · Cited by 398
Machine Learning for Computational Heterogeneous Catalysis
Schlexer Lamoureux, P., Winther, K. T., Garrido Torres, J. A., Streibel, V., Zhao, M., Bajdich, M., Abild‐Pedersen, F., & Bligaard, T. (2019) · ChemCatChem · doi:10.1002/cctc.201900595 · Cited by 356
Smith, J. S., Zubatyuk, R., Nebgen, B., Lubbers, N., Barros, K., Roitberg, A. E., Isayev, O., & Tretiak, S. (2020) · Scientific Data · doi:10.1038/s41597-020-0473-z · Cited by 280
Janet, J. P., Liu, F., Nandy, A., Duan, C., Yang, T., Lin, S., & Kulik, H. J. (2019) · Inorganic Chemistry · doi:10.1021/acs.inorgchem.9b00109 · Cited by 114
Metadata
- Authors
- Herr, J. E., Yao, K., McIntyre, R., Toth, D. W., & Parkhill, J.
- Venue
- The Journal of Chemical Physics
- Publisher
- AIP Publishing
- Published
- 2018-03-15
- Volume
- 148
- Issue
- 24
- Pages
- 241710-241710
- ISSN
- 0021-9606 (ISSN-L)
- 1089-7690
- OpenAlex
- W2779474077
- Cited by
- 77
- References
- 21
- FWCI
- 3.89
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.