arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.02637physics.chem-phcs.LG
收藏

自然科学中的数据集偏差:化学反应预测和合成设计的案例研究

Dataset Bias in the Natural Sciences: A Case Study in Chemical Reaction Prediction and Synthesis Design

University of Cambridge(剑桥大学);IBM Research Zurich(IBM苏黎世研究院)

Ryan-Rhys Griffiths, Philippe Schwaller, Alpha A. Lee

摘要:

自然科学中的数据集通常以帮助科学理解为目标,因此可能并不总是以促进机器学习应用的形式。在本文中,我们确定了化学反应预测和合成设计领域的三个趋势,需要改变方向。首先,将反应数据集分为反应物和试剂的方式鼓励以不切实际的慷慨方式测试模型。其次,我们强调了错误标记数据的普遍性,并建议重点应放在离群值去除上,而不仅仅是数据拟合。最后,除了反应物预测之外,我们还讨论了试剂预测问题,以解决完整的合成设计问题,突出了机器学习解决的问题与实验室化学家需要的问题之间的不匹配。我们的批评也与使用机器学习加速实验自然科学进展的新兴领域有关,其中数据集通常以有偏见的方式分裂,噪音很大,并且从数据中不明显的上下文变量强烈影响实验结果。

英文摘要:

Datasets in the Natural Sciences are often curated with the goal of aiding scientific understanding and hence may not always be in a form that facilitates the application of machine learning. In this paper, we identify three trends within the fields of chemical reaction prediction and synthesis design that require a change in direction. First, the manner in which reaction datasets are split into reactants and reagents encourages testing models in an unrealistically generous manner. Second, we highlight the prevalence of mislabelled data, and suggest that the focus should be on outlier removal rather than data fitting only. Lastly, we discuss the problem of reagent prediction, in addition to reactant prediction, in order to solve the full synthesis design problem, highlighting the mismatch between what machine learning solves and what a lab chemist would need. Our critiques are also relevant to the burgeoning field of using machine learning to accelerate progress in experimental Natural Sciences, where datasets are often split in a biased way, are highly noisy, and contextual variables that are not evident from the data strongly influence the outcome of experiments.

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。

↑