arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2111.04718cs.LGphysics.chem-phphysics.comp-phq-bio.QM
收藏

基于合成坐标的分子图上的有向信息传递

Directional Message Passing on Molecular Graphs via Synthetic Coordinates

Technical University of Munich(慕尼黑工业大学)

Johannes Gasteiger, Chandan Yeshwanth, Stephan Günnemann

摘要:

通过定向消息传递利用坐标的图神经网络最近已经在多个分子性质预测任务上设定了现有技术。然而,它们依赖于通常不可用的原子位置信息,并且获得它通常非常昂贵甚至不可能。在本文中,我们提出了合成坐标,使先进的GNNs的使用,而不需要真正的分子配置。我们提出了两个距离作为合成坐标:指定分子构型的粗略范围的距离界限,以及使用个性化PageRank的对称变体的基于图形的距离。为了利用距离和角度信息,我们提出了一种将正常图神经网络转换为有向MPNN的方法。我们表明,通过这种转换,我们可以减少55%的ZINC基准上的正常图神经网络的错误。此外,我们通过在SMP和DimeNet++模型中加入合成坐标,在ZINC和无坐标QM 9上设置了最新技术水平。我们的实现可在线获得。

英文摘要:

Graph neural networks that leverage coordinates via directional message passing have recently set the state of the art on multiple molecular property prediction tasks. However, they rely on atom position information that is often unavailable, and obtaining it is usually prohibitively expensive or even impossible. In this paper we propose synthetic coordinates that enable the use of advanced GNNs without requiring the true molecular configuration. We propose two distances as synthetic coordinates: Distance bounds that specify the rough range of molecular configurations, and graph-based distances using a symmetric variant of personalized PageRank. To leverage both distance and angular information we propose a method of transforming normal graph neural networks into directional MPNNs. We show that with this transformation we can reduce the error of a normal graph neural network by 55% on the ZINC benchmark. We furthermore set the state of the art on ZINC and coordinate-free QM9 by incorporating synthetic coordinates in the SMP and DimeNet++ models. Our implementation is available online.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑