The new work, accepted at the 2nd Workshop on Molecules and Materials hosted at NeurIPS 2018 this December is out. Here’s the abstract:
In this work, we extend the SchNet architecture by using weighted skip connections to assemble the final representation. This enables us to study the relative importance of each interaction block for property prediction. We demonstrate on both the QM9 and MD17 dataset that their relative weighting depends strongly on the chemical composition and configurational degrees of freedom of the molecules which opens the path towards a more detailed understanding of machine learning models for molecules.
For further information please refer to the ArXiv preprint Analysis of Atomistic Representations Using Weighted Skip-Connections
For any questions, remarks or curiosities feel free to contact me!