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 1704.01212cs.LG
收藏

量子化学中的神经信息传递

Neural Message Passing for Quantum Chemistry

Google Brain(谷歌大脑);Google(谷歌);Google DeepMind(谷歌DeepMind)

Justin Gilmer, Samuel S. Schoenholz, Patrick F. Riley, Oriol Vinyals, George E. Dahl

摘要:

分子上的监督学习在化学、药物发现和材料科学方面具有令人难以置信的潜力。幸运的是,文献中已经描述了几个有前途的和密切相关的分子对称性不变的神经网络模型。这些模型学习消息传递算法和聚合过程,以计算其整个输入图的函数。在这一点上,下一步是找到这种通用方法的一个特别有效的变体,并将其应用于化学预测基准,直到我们解决它们或达到该方法的极限。在本文中,我们将现有的模型重新制定为一个单一的通用框架,我们称之为消息传递神经网络(MPNNs),并在此框架内探索其他新的变化。使用MPNN,我们在一个重要的分子性质预测基准上展示了最先进的结果;这些结果足够强大,我们相信未来的工作应该集中在具有更大分子或更准确的地面真实标签的数据集上。

英文摘要:

Supervised learning on molecules has incredible potential to be useful in chemistry, drug discovery, and materials science. Luckily, several promising and closely related neural network models invariant to molecular symmetries have already been described in the literature. These models learn a message passing algorithm and aggregation procedure to compute a function of their entire input graph. At this point, the next step is to find a particularly effective variant of this general approach and apply it to chemical prediction benchmarks until we either solve them or reach the limits of the approach. In this paper, we reformulate existing models into a single common framework we call Message Passing Neural Networks (MPNNs) and explore additional novel variations within this framework. Using MPNNs we demonstrate state of the art results on an important molecular property prediction benchmark; these results are strong enough that we believe future work should focus on datasets with larger molecules or more accurate ground truth labels.

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。

↑