Abstract
Bayesian optimization (BO) is an effective method of finding the global optima of black-box functions. Recently BO has been applied to neural architecture search and shows better performance than pure evolutionary strategies. All these methods adopt Gaussian processes (GPs) as surrogate function, with the handcraft similarity metrics as input. In this work, we propose a Bayesian graph neural network as a new surrogate, which can automatically extract features from deep neural architectures, and use such learned features to fit and characterize black-box objectives and their uncertainty. Based on the new surrogate, we then develop a graph Bayesian optimization framework to address the challenging task of deep neural architecture search. Experiment results show our method significantly outperforms the comparative methods on benchmark tasks.
Abstract (translated)
贝叶斯优化(BO)是求黑盒函数全局最优的一种有效方法。近年来,BO已被应用于神经结构搜索,并显示出比纯进化策略更好的性能。所有这些方法都采用高斯过程(GPS)作为代理函数,以手工相似性度量作为输入。在这项工作中,我们提出了一种新的替代方法-贝叶斯图神经网络,它可以自动地从深层神经结构中提取特征,并利用这些学习到的特征来拟合和描述黑盒目标及其不确定性。在此基础上,我们开发了一个图贝叶斯优化框架来解决深度神经架构搜索的挑战性任务。实验结果表明,该方法在基准任务上明显优于比较法。
URL
https://arxiv.org/abs/1905.06159