Recent years have witnessed an upsurge of research interests and applications of machine learning on graphs. Automated machine learning (AutoML) on graphs is on the horizon to automatically design the optimal machine learning algorithm for a given graph task. However, all current libraries cannot support AutoML on graphs. To tackle this problem, we present Automated Graph Learning (AutoGL), the first library for automated machine learning on graphs. AutoGL is open-source, easy to use, and flexible to be extended. Specifically, We propose an automated machine learning pipeline for graph data containing four modules: auto feature engineering, model training, hyper-parameter optimization, and auto ensemble. For each module, we provide numerous state-of-the-art methods and flexible base classes and APIs, which allow easy customization. We further provide experimental results to showcase the usage of our AutoGL library.
翻译:近些年来,在图表上计算机学习的研究兴趣和应用激增。图表上的自动机学习(自动ML)即将自动设计一个最佳的图形任务机器学习算法。然而,目前所有图书馆都无法在图表上支持自动ML。为了解决这个问题,我们展示了图上自动机器学习的第一个图书馆自动图学习(AutoGL),AutoGL是开放源,易于使用,灵活扩展。具体地说,我们提议为包含四个模块的图形数据建立一个自动机学习管道:自动地物工程、模型培训、超参数优化和自动共融。我们为每个模块提供许多最先进的方法和灵活的基础班和API,以方便用户的定制。我们进一步提供实验结果,以展示我们的AutoGL图书馆的使用情况。