Abstract
Graph Neural Networks (GNNs) have been popularly used for analyzing non-Euclidean data such as social network data and biological data. Despite their success, the design of graph neural networks requires a lot of manual work and domain knowledge. In this paper, we propose a Graph Neural Architecture Search method (GraphNAS for short) that enables automatic search of the best graph neural architecture based on reinforcement learning. Specifically, GraphNAS first uses a recurrent network to generate variable-length strings that describe the architectures of graph neural networks, and then trains the recurrent network with reinforcement learning to maximize the expected accuracy of the generated architectures on a validation data set. Extensive experimental results on node classification tasks in both transductive and inductive learning settings demonstrate that GraphNAS can achieve consistently better performance on the Cora, Citeseer, Pubmed citation network, and protein-protein interaction network. On node classification tasks, GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy.
Abstract (translated)
图神经网络(GNN)已广泛用于分析非欧几里得数据,如社会网络数据和生物数据。尽管取得了成功,但图形神经网络的设计仍需要大量的人工操作和领域知识。本文提出了一种基于增强学习的图神经结构自动搜索方法(graphnas简称graphnas)。具体来说,graphnas首先使用循环网络生成描述图神经网络结构的可变长度字符串,然后通过强化学习训练循环网络,以最大限度地提高生成的结构对验证数据集的预期精度。在转导和诱导学习环境下,对节点分类任务的大量实验结果表明,graphnas可以在cora、citeseer、pubmed引文网络和蛋白质相互作用网络上持续获得更好的性能。在节点分类任务中,graphnas可以设计一种新的网络体系结构,在测试集精度方面与人类发明的最佳体系结构相竞争。
URL
https://arxiv.org/abs/1904.09981