Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Cormorant: Covariant Molecular Neural Networks
Authors: Brandon Anderson, Truong Son Hy, Risi Kondor
NeurIPS 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We apply these networks to molecular systems with two goals: learning atomic potential energy surfaces for use in Molecular Dynamics simulations, and learning ground state properties of molecules calculated by Density Functional Theory. Cormorant significantly outperforms competing algorithms in learning molecular Potential Energy Surfaces from conformational geometries in the MD-17 dataset, and is competitive with other methods at learning geometric, energetic, electronic, and thermodynamic properties of molecules on the GDB-9 dataset. We present experimental results on two datasets of interest to the computational chemistry community: MD-17 for learning molecular force fields and potential energy surfaces, and QM-9 for learning the ground state properties of a set of molecules. |
| Researcher Affiliation | Collaboration | Brandon Anderson , Truong-Son Hy and Risi Kondor Department of Computer Science, Department of Statistics The University of Chicago Center for Computational Mathematics, Flatiron Institute Atomwise EMAIL EMAIL |
| Pseudocode | No | The paper describes the architecture and operations mathematically but does not include any pseudocode or clearly labeled algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/risilab/cormorant. |
| Open Datasets | Yes | QM9 [Ramakrishnan et al., 2014] is a dataset of approximately 134k small organic molecules containing the atoms H, C, N, O, F. MD-17 [Chmiela et al., 2016] is a dataset of eight small organic molecules (see Table 1(b)) containing up to 17 total atoms composed of the atoms H, C, N, O, F. |
| Dataset Splits | Yes | For each molecule we use a train/validation/test split of 50k/10k/10k atoms respectively. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU, GPU models, or cloud instance types) used for running experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | No | The supplement provides a detailed summary of all hyperparameters, our training algorithm, and the details of the input/output levels used in both cases. |