An ensemble of VisNet, Transformer-M, and pretraining models for molecular property prediction in OGB Large-Scale Challenge @ NeurIPS 2022
This work addresses molecular property prediction for computational chemistry, representing a competitive but incremental improvement in a domain-specific challenge.
The authors tackled molecular property prediction for quantum chemical HOMO-LUMO gaps on the PCQM4Mv2 dataset, achieving a mean absolute error of 0.0723 eV with an ensemble of 22 models, which reduced error by 39.75% compared to the previous best method.
In the technical report, we provide our solution for OGB-LSC 2022 Graph Regression Task. The target of this task is to predict the quantum chemical property, HOMO-LUMO gap for a given molecule on PCQM4Mv2 dataset. In the competition, we designed two kinds of models: Transformer-M-ViSNet which is an geometry-enhanced graph neural network for fully connected molecular graphs and Pretrained-3D-ViSNet which is a pretrained ViSNet by distilling geomeotric information from optimized structures. With an ensemble of 22 models, ViSNet Team achieved the MAE of 0.0723 eV on the test-challenge set, dramatically reducing the error by 39.75% compared with the best method in the last year competition.