GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets

TL;DR

This paper introduces GemNet-OC, a graph neural network optimized for large, diverse molecular datasets, demonstrating significant performance improvements and efficiency, and highlighting the importance of representative datasets for generalizable GNN development.

Contribution

The paper develops GemNet-OC, a GNN tailored for large-scale molecular datasets, and systematically analyzes dataset complexity impacts on model performance and development practices.

Findings

GemNet-OC outperforms previous models on OC20 by 16%.

Training time is reduced by a factor of 10 with GemNet-OC.

Results on OC-2M dataset correlate well with full OC20 performance.

Abstract

Recent years have seen the advent of molecular simulation datasets that are orders of magnitude larger and more diverse. These new datasets differ substantially in four aspects of complexity: 1. Chemical diversity (number of different elements), 2. system size (number of atoms per sample), 3. dataset size (number of data samples), and 4. domain shift (similarity of the training and test set). Despite these large differences, benchmarks on small and narrow datasets remain the predominant method of demonstrating progress in graph neural networks (GNNs) for molecular simulation, likely due to cheaper training compute requirements. This raises the question -- does GNN progress on small and narrow datasets translate to these more complex datasets? This work investigates this question by first developing the GemNet-OC model based on the large Open Catalyst 2020 (OC20) dataset. GemNet-OC outperforms the previous state-of-the-art on OC20 by 16% while reducing training time by a factor of 10. We then compare the impact of 18 model components and hyperparameter choices on performance in multiple datasets. We find that the resulting model would be drastically different depending on the dataset used for making model choices. To isolate the source of this discrepancy we study six subsets of the OC20 dataset that individually test each of the above-mentioned four dataset aspects. We find that results on the OC-2M subset correlate well with the full OC20 dataset while being substantially cheaper to train on. Our findings challenge the common practice of developing GNNs solely on small datasets, but highlight ways of achieving fast development cycles and generalizable results via moderately-sized, representative datasets such as OC-2M and efficient models such as GemNet-OC. Our code and pretrained model weights are open-sourced.