Recent advances in artificial intelligence largely benefit from better neural network architectures. These architectures are a product of a costly process of trial-and-error. To ease this process, we develop ArchExplorer, a visual analysis method for understanding a neural architecture space and summarizing design principles. The key idea behind our method is to make the architecture space explainable by exploiting structural distances between architectures. We formulate the pairwise distance calculation as solving an all-pairs shortest path problem. To improve efficiency, we decompose this problem into a set of single-source shortest path problems. The time complexity is reduced from O(kn^2N) to O(knN). Architectures are hierarchically clustered according to the distances between them. A circle-packing-based architecture visualization has been developed to convey both the global relationships between clusters and local neighborhoods of the architectures in each cluster. Two case studies and a post-analysis are presented to demonstrate the effectiveness of ArchExplorer in summarizing design principles and selecting better-performing architectures.
翻译:人工智能的最近进步在很大程度上得益于更好的神经网络结构。 这些建筑是昂贵的试验和操作过程的产物。 为了缓解这一过程, 我们开发了Arch Explorer, 这是理解神经结构空间和总结设计原则的视觉分析方法。 我们的方法背后的关键思想是使建筑空间能够通过利用建筑结构之间的结构距离来解释。 我们将配对距离计算方法设计成解决全孔最短路径问题的方法。 为了提高效率, 我们将这一问题分解成一套单一来源的最短路径问题。 时间复杂性从 O( kn%2N) 降低到 O( knN) 。 建筑按它们之间的距离按等级分组组合。 基于圆包的建筑已开发了视觉化, 以传达每组结构的集群和当地周边之间的全球关系。 我们提出了两个案例研究和后分析, 以展示ArchExtorerer在总结设计原则和选择更好表现的结构方面的有效性 。