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 2102.07916cs.LGcs.SI
收藏

基于Few-Shot图学习的分子性质预测

Few-Shot Graph Learning for Molecular Property Prediction

University of Notre Dame(圣母大学);Brandeis University(布兰迪斯大学)

Zhichun Guo, Chuxu Zhang, Wenhao Yu, John Herr, Olaf Wiest, Meng Jiang, Nitesh V. Chawla

摘要:

最近图神经网络的成功极大地促进了分子性质预测,推进了药物发现等活动。现有的深度神经网络方法通常需要针对每个性质的大的训练数据集,这在具有有限数量的实验数据的情况下(特别是对于新的分子性质)损害了它们的性能,这在实际情况中是常见的。为此,我们提出了Meta-MGNN,一种新的Few-Shot分子性质预测模型。Meta-MGNN采用分子图神经网络学习分子表示,构建了模型优化的元学习框架。为了利用未标记的分子信息和解决不同分子特性的任务异质性,Meta-MGNN进一步将分子结构,基于属性的自监督模块和自关注任务权重纳入前一个框架,加强了整个学习模型。在两个公共多属性数据集上的大量实验表明,Meta-MGNN优于各种最先进的方法。

英文摘要:

The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery. The existing deep neural network methods usually require large training dataset for each property, impairing their performances in cases (especially for new molecular properties) with a limited amount of experimental data, which are common in real situations. To this end, we propose Meta-MGNN, a novel model for few-shot molecular property prediction. Meta-MGNN applies molecular graph neural network to learn molecular representation and builds a meta-learning framework for model optimization. To exploit unlabeled molecular information and address task heterogeneity of different molecular properties, Meta-MGNN further incorporates molecular structure, attribute based self-supervised modules and self-attentive task weights into the former framework, strengthening the whole learning model. Extensive experiments on two public multi-property datasets demonstrate that Meta-MGNN outperforms a variety of state-of-the-art methods.

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。

↑