arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2010.07474cs.LGcs.AI
收藏

Auto-STGCN:基于强化学习和已有研究成果的自主时空图卷积网络搜索

Auto-STGCN: Autonomous Spatial-Temporal Graph Convolutional Network Search Based on Reinforcement Learning and Existing Research Results

Harbin Institute of Technology(哈尔滨工业大学);Peng Cheng Laboratory(鹏城实验室)

Chunnan Wang, Kaixin Zhang, Hongzhi Wang, Bozhou Chen

摘要:

近年来,人们提出了许多时空图卷积网络(STGCN)模型来处理时空网络数据预测问题。这些STGCN模型有其自身的优点,即,它们各自提出了许多有效的运算,并在实际应用中取得了较好的预测效果。如果用户能够有效地利用和组合这些优秀的操作,结合现有模型的优点,那么他们可能会获得更有效的STGCN模型,从而利用现有的工作创造更大的价值。然而,由于缺乏领域知识,他们无法做到这一点,并且缺乏自动化系统来帮助用户实现这一目标。本文填补了这一空白,提出了Auto-STGCN算法,该算法利用现有模型自动探索特定场景下的高性能STGCN模型。具体而言,本文设计了Unified-STGCN框架,该框架对现有体系结构的操作进行了总结,并使用参数控制每个操作的用法和特征属性,从而实现了STGCN体系结构的参数化表示和优势的重组与融合。然后,我们提出了Auto-STGCN,一种基于强化学习的优化方法,快速搜索Unified-STGCN提供的参数搜索空间,自动生成最优的STGCN模型。在真实世界基准数据集上的大量实验表明,我们的Auto-STGCN可以找到优于现有STGCN模型的启发式参数,这表明我们提出的方法的有效性。

英文摘要:

In recent years, many spatial-temporal graph convolutional network (STGCN) models are proposed to deal with the spatial-temporal network data forecasting problem. These STGCN models have their own advantages, i.e., each of them puts forward many effective operations and achieves good prediction results in the real applications. If users can effectively utilize and combine these excellent operations integrating the advantages of existing models, then they may obtain more effective STGCN models thus create greater value using existing work. However, they fail to do so due to the lack of domain knowledge, and there is lack of automated system to help users to achieve this goal. In this paper, we fill this gap and propose Auto-STGCN algorithm, which makes use of existing models to automatically explore high-performance STGCN model for specific scenarios. Specifically, we design Unified-STGCN framework, which summarizes the operations of existing architectures, and use parameters to control the usage and characteristic attributes of each operation, so as to realize the parameterized representation of the STGCN architecture and the reorganization and fusion of advantages. Then, we present Auto-STGCN, an optimization method based on reinforcement learning, to quickly search the parameter search space provided by Unified-STGCN, and generate optimal STGCN models automatically. Extensive experiments on real-world benchmark datasets show that our Auto-STGCN can find STGCN models superior to existing STGCN models with heuristic parameters, which demonstrates the effectiveness of our proposed method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑