.png){kind=icon}
返回
Graph Neural Network-Based Molecular Property Prediction with Patch Aggregation
.png){kind=icon}
PRE
AI
DOI：10.1021/acs.jctc.4c00798.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph neural networks (GNNs) have emerged as powerful tools for quantum chemical property prediction, leveraging the inherent graph structure of molecular systems. GNNs depend on an edge-to-node aggregation mechanism for combining edge representations into node representations. Unfortunately, existing learnable edge-to-node aggregation methods substantially increase the number of parameters and, thus, the computational cost relative to simple sum aggregation. Worse, as we report here, they often fail to improve predictive accuracy. We therefore propose a novel learnable edge-to-node aggregation mechanism that aims to improve the accuracy and parameter efficiency of GNNs in predicting molecular properties. The new mechanism, called patch aggregation, is inspired by the Multi-Head Attention and Mixture of Experts machine learning techniques. We have incorporated the patch aggregation method into the specialized, state-of-the-art GNN models SchNet, DimeNet++, SphereNet, TensorNet, and VisNet and show that patch aggregation consistently outperforms existing learnable and nonlearnable aggregation techniques (sum, multilayer perceptron, softmax, and set transformer aggregation) in the prediction of molecular properties such as QM9 thermodynamic properties and MD17 molecular dynamics trajectory energies and forces. We also find that patch aggregation not only improves prediction accuracy but also is parameter-efficient, making it an attractive option for practical applications for which computational resources are limited. Further, we show that Patch aggregation can be applied across different GNN models. Overall, Patch aggregation is a powerful edge-to-node aggregation mechanism that improves the accuracy of molecular property predictions by GNNs.
期刊
IF:
5.5
论文数:
1.1W
被引数:
5.4W
机构
引用论文
Approaching coupled cluster accuracy with a general-purpose neural network potential through transfer learning通过迁移学习接近具有通用神经网络潜力的耦合聚类精度.png)
NATURE COMMUNICATIONS
OAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏Attention is all you need: utilizing attention in AI-enabled drug discovery注意力是你所需要的: 在人工智能药物发现中利用注意力OAAI
OAAI分享收藏Machine learning of accurate energy-conserving molecular force fields精确能量保存分子力场的机器学习SCIENCE ADVANCESOAAI
SCIENCE ADVANCESIF12.5
OAAI分享收藏Screening of wastewater Oedogonium oblangum algae for hyper-oil transformation into biodiesel by response surface methodology通过响应面法筛选废水中的Oedogonium oblangum藻类，以实现高油转化生物柴油。OAAI
OAAI分享收藏Enhancing geometric representations for molecules with equivariant vector-scalar interactive message passing通过等变矢量标量交互式消息传递增强分子的几何表示NATURE COMMUNICATIONSOAAI
NATURE COMMUNICATIONSIF15.7
OAAI分享收藏ANI-1: an extensible neural network potential with DFT accuracy at force field computational costANI-1: 在力场计算成本下具有DFT精度的可扩展神经网络潜力Chemical ScienceOAAI
Chemical ScienceIF7.4
OAAI分享收藏
查看更多内容