Analysis of Atomistic Representations Using Weighted Skip-Connections

2018/10/23 by Kim A. Nicoli, Pan Kessel, Nicoli, Kim A. +5
Computer Science · Materials Science · #Chemical Physics (physics.chem-ph) #Computational Drug Discovery Methods #Computational Physics (physics.comp-ph) #Enzyme Structure and Function #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (stat.ML) #Machine Learning in Materials Science

paper · pdf · doi:10.48550/arxiv.1810.09751

openalex publication_date 2018/10/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Citations

• SGDR: Stochastic Gradient Descent with Warm Restarts
• Quantum-chemical insights from deep tensor neural networks
• Learning how to explain neural networks: PatternNet and PatternAttribution
• SchNet – A deep learning architecture for molecules and materials
• Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps

Related

• Stacked Generalization Approach to Improve Prediction of Molecular Atomization Energies
• Distributed Representations of Atoms and Materials for Machine Learning
• Atom-Density Representations for Machine Learning
• Taming Multi-Domain, -Fidelity Data: Towards Foundation Models for Atomistic Scale Simulations
• Analyzing Atomic Interactions in Molecules as Learned by Neural Networks