Yujia Li, Daniel Tarlow, Marc Brockschmidt, Richard Zemel
TL;DR本论文研究图结构数据的学习技术，以 Graph Neural Networks 为起点，使用门控循环单元和现代优化技术，并将其扩展为输出序列，展示出其在一些简单的 AI 和图算法学习任务中的能力，并在程序验证的问题中实现了最新水平的性能。
Abstract
graph-structured data appears frequently in domains including chemistry, natural language semantics, social networks, and knowledge bases. In this work, we study feature learning techniques for graph-structured i