论文标题
大规模分子建模数据集上的基准测量图形器
Benchmarking Graphormer on Large-Scale Molecular Modeling Datasets
论文作者
论文摘要
该技术说明描述了图形配置器的最新更新，包括体系结构设计修改以及对3D分子动力学仿真的适应。有了这些简单的修改，图形师可以在大规模分子建模数据集上获得更好的结果，而不是香草一号，并且可以在2D和3D分子图建模任务上始终获得性能增益。此外，我们表明，借助全球接收场和自适应聚合策略，Graphormer比经典的基于消息的GNN更强大。 Empirically, Graphormer could achieve much less MAE than the originally reported results on the PCQM4M quantum chemistry dataset used in KDD Cup 2021. In the meanwhile, it greatly outperforms the competitors in the recent Open Catalyst Challenge, which is a competition track on NeurIPS 2021 workshop, and aims to model the catalyst-adsorbate reaction system with advanced AI models.所有代码均可在https://github.com/microsoft/graphormer上找到。
This technical note describes the recent updates of Graphormer, including architecture design modifications, and the adaption to 3D molecular dynamics simulation. With these simple modifications, Graphormer could attain better results on large-scale molecular modeling datasets than the vanilla one, and the performance gain could be consistently obtained on 2D and 3D molecular graph modeling tasks. In addition, we show that with a global receptive field and an adaptive aggregation strategy, Graphormer is more powerful than classic message-passing-based GNNs. Empirically, Graphormer could achieve much less MAE than the originally reported results on the PCQM4M quantum chemistry dataset used in KDD Cup 2021. In the meanwhile, it greatly outperforms the competitors in the recent Open Catalyst Challenge, which is a competition track on NeurIPS 2021 workshop, and aims to model the catalyst-adsorbate reaction system with advanced AI models. All codes could be found at https://github.com/Microsoft/Graphormer.
