论文标题
通过Weisfeiler-Lehman内核通过贝叶斯优化通过贝叶斯优化来解释的神经建筑搜索
Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels
论文作者
论文摘要
当前的神经体系结构搜索（NAS）策略仅着眼于寻找单个，良好的建筑。他们对特定网络为何表现良好，或者如果我们想要进一步的改进应该如何修改体系结构，几乎没有洞察力。我们为NAS提出了一种贝叶斯优化方法（BO）方法，该方法将Weisfeiler-Lehman图内核与高斯工艺代理结合在一起。我们的方法以高度数据效率的方式优化了体系结构：它能够捕获体系结构的拓扑结构并可以扩展到大图，从而使高维和图形搜索空间可易于BO。更重要的是，我们的方法通过发现有用的网络功能及其对网络性能的相应影响来提供解释性。确实，我们从经验上证明，我们的替代模型能够识别有用的主题，从而指导新的体系结构的产生。我们最终表明，我们的方法优于现有的NAS方法，可以在闭合和开放域搜索空间上实现最新技术。
Current neural architecture search (NAS) strategies focus only on finding a single, good, architecture. They offer little insight into why a specific network is performing well, or how we should modify the architecture if we want further improvements. We propose a Bayesian optimisation (BO) approach for NAS that combines the Weisfeiler-Lehman graph kernel with a Gaussian process surrogate. Our method optimises the architecture in a highly data-efficient manner: it is capable of capturing the topological structures of the architectures and is scalable to large graphs, thus making the high-dimensional and graph-like search spaces amenable to BO. More importantly, our method affords interpretability by discovering useful network features and their corresponding impact on the network performance. Indeed, we demonstrate empirically that our surrogate model is capable of identifying useful motifs which can guide the generation of new architectures. We finally show that our method outperforms existing NAS approaches to achieve the state of the art on both closed- and open-domain search spaces.
