Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
This work addresses the challenge of accurate and interpretable molecule property prediction for computational chemistry, representing an incremental improvement with a novel method.
The authors tackled the problem of predicting molecule properties by developing a machine learning algorithm that uses solid harmonic scattering coefficients derived from surrogate electronic densities, achieving near state-of-the-art performance with few training examples and reaching DFT precision in predictions.
We present a machine learning algorithm for the prediction of molecule properties inspired by ideas from density functional theory. 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. Multi-linear 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.