Constrained Bayesian optimization for automatic chemical design using variational autoencoders
Constrained Bayesian optimization for automatic chemical design using variational autoencoders
复制标题
DOI：
10.1039/c9sc04026a
复制
发表时间：
2020-01-14
期刊：
影响因子：
8.4
通讯作者：
Hernandez-Lobato, Jose Miguel
中科院分区：
文献类型：
--
作者：
Griffiths, Ryan-Rhys;Hernandez-Lobato, Jose Miguel
自动化学设计是一个框架，用于生成具有优化特性的新型分子。原来的计划，具有贝叶斯优化的潜在空间的变分自动编码器，遭受的病理，它往往会产生无效的分子结构。首先，我们根据经验证明，当贝叶斯优化方案查询远离变分自动编码器已被训练的数据的潜在空间点时，会出现这种病理。其次，通过重新制定的搜索过程作为一个约束贝叶斯优化问题，我们表明，这种病理的影响可以减轻，产生显着改善所产生的分子的有效性。我们认为，约束贝叶斯优化是解决这种训练集不匹配的一个很好的方法，在许多生成任务涉及贝叶斯优化的潜在空间的变分自动编码器。
Automatic Chemical Design is a framework for generating novel molecules with optimized properties. The original scheme, featuring Bayesian optimization over the latent space of a variational autoencoder, suffers from the pathology that it tends to produce invalid molecular structures. First, we demonstrate empirically that this pathology arises when the Bayesian optimization scheme queries latent space points far away from the data on which the variational autoencoder has been trained. Secondly, by reformulating the search procedure as a constrained Bayesian optimization problem, we show that the effects of this pathology can be mitigated, yielding marked improvements in the validity of the generated molecules. We posit that constrained Bayesian optimization is a good approach for solving this kind of training set mismatch in many generative tasks involving Bayesian optimization over the latent space of a variational autoencoder.