Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directions
This work provides a systematic framework for automating graph machine learning, which is incremental as it builds on existing automated machine learning techniques but applies them specifically to graph-related tasks.
The paper addresses the challenge of manually designing optimal graph machine learning algorithms by introducing automated approaches, including hyper-parameter optimization and neural architecture search, and presents AutoGL as the first open-source library for this purpose along with a tailored benchmark for evaluation.
Graph machine learning has been extensively studied in both academic and industry. However, as the literature on graph learning booms with a vast number of emerging methods and techniques, it becomes increasingly difficult to manually design the optimal machine learning algorithm for different graph-related tasks. To tackle the challenge, automated graph machine learning, which aims at discovering the best hyper-parameter and neural architecture configuration for different graph tasks/data without manual design, is gaining an increasing number of attentions from the research community. In this paper, we extensively discuss automated graph machine learning approaches, covering hyper-parameter optimization (HPO) and neural architecture search (NAS) for graph machine learning. We briefly overview existing libraries designed for either graph machine learning or automated machine learning respectively, and further in depth introduce AutoGL, our dedicated and the world's first open-source library for automated graph machine learning. Also, we describe a tailored benchmark that supports unified, reproducible, and efficient evaluations. Last but not least, we share our insights on future research directions for automated graph machine learning. This paper is the first systematic and comprehensive discussion of approaches, libraries as well as directions for automated graph machine learning.