Automated Machine Learning on Graphs: A Survey

TL;DR

This paper provides a comprehensive survey of automated machine learning techniques applied to graph data, focusing on hyper-parameter optimization and neural architecture search, and discusses related tools and future directions.

Contribution

It is the first systematic review of AutoML on graphs, covering methods, tools, and future research directions in this emerging field.

Findings

Overview of AutoML techniques for graphs

Discussion of AutoML libraries including AutoGL

Identification of future research challenges and directions

Abstract

Machine learning on graphs 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 solve this critical challenge, automated machine learning (AutoML) on graphs which combines the strength of graph machine learning and AutoML together, is gaining attention from the research community. Therefore, we comprehensively survey AutoML on graphs in this paper, primarily focusing on hyper-parameter optimization (HPO) and neural architecture search (NAS) for graph machine learning. We further overview libraries related to automated graph machine learning and in-depth discuss AutoGL, the first dedicated open-source library for AutoML on graphs. In the end, we share our insights on future research directions for automated graph machine learning. This paper is the first systematic and comprehensive review of automated machine learning on graphs to the best of our knowledge.