LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction
This work addresses quantum property prediction for chemistry applications, but it appears incremental as it builds on existing graph neural network and self-supervised learning techniques.
The authors tackled the problem of predicting HOMO-LUMO gaps of molecules using the PCQM4M-LSC dataset, achieving a mean absolute error of 0.1204 on the test set with their LiteGEM method.
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/.