arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.14766cond-mat.mtrl-sci
收藏

MODNet -通过特征选择和联合学习对有限材料数据集进行准确和可解释的属性预测

MODNet -- accurate and interpretable property predictions for limited materials datasets by feature selection and joint-learning

Pierre-Paul De Breuck, Geoffroy Hautier, Gian-Marco Rignanese

摘要:

为了准确预测材料特性,目前的机器学习方法通常需要大量的数据,而这些数据在实践中往往是不可用的。在这项工作中,提出了一个全面的框架,它依赖于前馈神经网络,选择物理上有意义的功能,并在适用的情况下,联合学习。除了在训练时间方面更快之外,这种方法在小数据集上的表现优于当前的图网络模型。特别是,在305 K的晶体的振动熵预测的平均绝对测试误差为0.009 meV/K/原子(比以前的研究低四倍)。此外,与单目标学习相比,联合学习减少了测试误差,并能够同时预测多个属性,例如温度函数。最后,选择算法突出了最重要的特征,从而有助于理解底层物理。

英文摘要:

In order to make accurate predictions of material properties, current machine-learning approaches generally require large amounts of data, which are often not available in practice. In this work, an all-round framework is presented which relies on a feedforward neural network, the selection of physically-meaningful features and, when applicable, joint-learning. Next to being faster in terms of training time, this approach is shown to outperform current graph-network models on small datasets. In particular, the vibrational entropy at 305 K of crystals is predicted with a mean absolute test error of 0.009 meV/K/atom (four times lower than previous studies). Furthermore, joint-learning reduces the test error compared to single-target learning and enables the prediction of multiple properties at once, such as temperature functions. Finally, the selection algorithm highlights the most important features and thus helps understanding the underlying physics.

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。

↑