论文标题
GPS ++：用于分子性质预测的优化杂交MPNN/变压器
GPS++: An Optimised Hybrid MPNN/Transformer for Molecular Property Prediction
论文作者
论文摘要
该技术报告提出了GPS ++，这是针对PCQM4MV2分子属性预测任务的开放图基准大规模挑战（OGB-LSC 2022）的第一名解决方案。我们的方法实现了先前文献中的几个关键原则。我们的GPS ++方法的核心是一种混合MPNN/变压器模型，该模型结合了3D原子位置和辅助DeNoising任务。通过在独立的测试 - 挑战PCQM4MV2拆分上实现0.0719平均绝对误差来证明GPS ++的有效性。得益于IPU加速度的GraphCore，GPS ++量表可缩放到深度体系结构（16层），每年3分钟的训练和大型合奏（112型型号），完成了1小时32分钟的最终预测，远低于分配的4小时推进预算。我们的实现可在以下网址公开获取：https：//github.com/graphcore/ogb-lsc-pcqm4mv2。
This technical report presents GPS++, the first-place solution to the Open Graph Benchmark Large-Scale Challenge (OGB-LSC 2022) for the PCQM4Mv2 molecular property prediction task. Our approach implements several key principles from the prior literature. At its core our GPS++ method is a hybrid MPNN/Transformer model that incorporates 3D atom positions and an auxiliary denoising task. The effectiveness of GPS++ is demonstrated by achieving 0.0719 mean absolute error on the independent test-challenge PCQM4Mv2 split. Thanks to Graphcore IPU acceleration, GPS++ scales to deep architectures (16 layers), training at 3 minutes per epoch, and large ensemble (112 models), completing the final predictions in 1 hour 32 minutes, well under the 4 hour inference budget allocated. Our implementation is publicly available at: https://github.com/graphcore/ogb-lsc-pcqm4mv2.
