Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
By Michael Eickenberg, Georgios Exarchakis, Matthew J. Hirn, Stéphane Mallat, L. Thiry. 2018
79 citations recorded by the source corpus.
We present a machine learning algorithm for the prediction of molecule properties inspired by ideas from density functional theory (DFT). Using Gaussian-type orbital functions, we create surrogate electronic densities of the molecule from which we compute invariant "solid harmonic scattering coefficients" that account for different types of interactions at different scales. Multilinear regressions of various physical properties of molecules are computed from these invariant coefficients. Numerical experiments show that these regressions have near state-of-the-art performance, even with relatively few training examples. Predictions over small sets of scattering coefficients can reach a DFT precision while being interpretable.
Subfields: Computational Theory and Mathematics, Materials Chemistry
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
- Javier Llorca
- Matthew J. Hirn
- Stéphane Mallat
- Joan Bruna
- Ellad B. Tadmor
- Michael Eickenberg
- Gábor Csányi
- Georgios Exarchakis
In Materials Chemistry
- Stéphane Mallat
- Matthew J. Hirn
- Javier Llorca
- Mgd Marc Geers
- Wei Cai
- S. Foiles
- Gábor Csányi
- Vasily V. Bulatov
Citations in the corpus
- Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models (2018, unknown): “between atoms. Their generalization can be seen as tensors that encode multiple symmetries and physical properties of atoms [67]. The use of electronic densities has also been explored for prediction [68]. Another representation has relied on position molecules within a 3D grid space, often with cha”
- Kymatio: Scattering Transforms in Python (2018, methodology): “…comparison of existing implementations: ScatNet (And´en et al., 2014), ScatNetLight (Oyallon and Mallat, 2015), PyScatWave (Oyallon et al., 2018), Scattering.m (Lostanlen and Mallat, 2015), PyScatHarm (Eickenberg et al., 2018), and the scattering transform implemented in the MATLAB Wavelet Toolbox.”
- Roadmap on multiscale materials modeling (2020, background): “(The one exception uses wavelet transforms to capture the global atom-density on multiple length scales [60].”