LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction

06/28/2021

∙

In this report, we (SuperHelix team) present our solution to KDD Cup 2021-PCQM4M-LSC, a large-scale quantum chemistry dataset on predicting HOMO-LUMO gap of molecules. Our solution, Lite Geometry Enhanced Molecular representation learning (LiteGEM) achieves a mean absolute error (MAE) of 0.1204 on the test set with the help of deep graph neural networks and various self-supervised learning tasks. The code of the framework can be found in https://github.com/PaddlePaddle/PaddleHelix/tree/dev/competition/kddcup2021-PCQM4M-LSC/.

READ FULL TEXT

LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction

An ensemble of VisNet, Transformer-M, and pretraining models for molecular property prediction in OGB Large-Scale Challenge @ NeurIPS 2022

Towards IID representation learning and its application on biomedical data

An Empirical Study of Graphormer on Large-Scale Molecular Modeling Datasets

Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets

Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction

Molecular CT: Unifying Geometry and Representation Learning for Molecules at Different Scales

Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian

LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction

Related Research

An ensemble of VisNet, Transformer-M, and pretraining models for molecular property prediction in OGB Large-Scale Challenge @ NeurIPS 2022

Towards IID representation learning and its application on biomedical data

An Empirical Study of Graphormer on Large-Scale Molecular Modeling Datasets

Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets

Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction

Molecular CT: Unifying Geometry and Representation Learning for Molecules at Different Scales

Efficient and Equivariant Graph Networks for Predicting Quantum Hamiltonian