论文标题
DFG-NAS：深而灵活的图形神经体系结构搜索
DFG-NAS: Deep and Flexible Graph Neural Architecture Search
论文作者
论文摘要
图形神经网络（GNN）已被密切应用于各种基于图的应用程序。尽管他们成功了，但手动设计行为良好的GNN需要巨大的人类专业知识。因此，发现潜在的最佳数据特异性GNN体系结构效率低下。本文提出了DFG-NAS，这是一种新的神经体系结构搜索（NAS）方法，可自动搜索非常深入且灵活的GNN体系结构。与大多数专注于微构造的方法不同，DFG-NAS突出了另一个设计级别：搜索有关原子传播的宏观结构（\ textbf {\ textbf {\ texttt {p}}}）和转换（\ textbf {\ texttt {t texttt {t}}}）的操作和有组织。为此，DFG-NAS为\ textbf {\ texttt {p-t}}的排列和组合提出了一个新颖的搜索空间，并基于消息通讯的散布聚集，定义了四个自定义设计的宏观体系结构突变，并采用进化性algorithm来进行有效和有效的搜索。关于四个节点分类任务的实证研究表明，DFG-NAS优于最先进的手动设计和GNN的NAS方法。
Graph neural networks (GNNs) have been intensively applied to various graph-based applications. Despite their success, manually designing the well-behaved GNNs requires immense human expertise. And thus it is inefficient to discover the potentially optimal data-specific GNN architecture. This paper proposes DFG-NAS, a new neural architecture search (NAS) method that enables the automatic search of very deep and flexible GNN architectures. Unlike most existing methods that focus on micro-architectures, DFG-NAS highlights another level of design: the search for macro-architectures on how atomic propagation (\textbf{\texttt{P}}) and transformation (\textbf{\texttt{T}}) operations are integrated and organized into a GNN. To this end, DFG-NAS proposes a novel search space for \textbf{\texttt{P-T}} permutations and combinations based on message-passing dis-aggregation, defines four custom-designed macro-architecture mutations, and employs the evolutionary algorithm to conduct an efficient and effective search. Empirical studies on four node classification tasks demonstrate that DFG-NAS outperforms state-of-the-art manual designs and NAS methods of GNNs.
