Curriculum Graph Machine Learning: A Survey

TL;DR

Graph CL addresses suboptimal optimization from random training orders in graph learning by integrating curriculum learning with graph neural networks. The survey formalizes the Graph CL problem, and systematically categorizes methods into node-, link-, and graph-level tasks, further splitting them into predefined and automatic curricula. It highlights representative approaches across these categories, detailing how difficulty measures and schedulers are designed and applied. The paper also discusses theoretical, practical, and application-driven future directions, emphasizing the need for principled models, robust evaluation, and broader real-world use cases.

Abstract

Graph machine learning has been extensively studied in both academia and industry. However, in the literature, most existing graph machine learning models are designed to conduct training with data samples in a random order, which may suffer from suboptimal performance due to ignoring the importance of different graph data samples and their training orders for the model optimization status. To tackle this critical problem, curriculum graph machine learning (Graph CL), which integrates the strength of graph machine learning and curriculum learning, arises and attracts an increasing amount of attention from the research community. Therefore, in this paper, we comprehensively overview approaches on Graph CL and present a detailed survey of recent advances in this direction. Specifically, we first discuss the key challenges of Graph CL and provide its formal problem definition. Then, we categorize and summarize existing methods into three classes based on three kinds of graph machine learning tasks, i.e., node-level, link-level, and graph-level tasks. Finally, we share our thoughts on future research directions. To the best of our knowledge, this paper is the first survey for curriculum graph machine learning.