Graph Self-Supervised Learning: A Survey
Graph Self-Supervised Learning: A Survey
复制标题
图自监督学习：综述
DOI：
10.1109/tkde.2022.3172903
复制
发表时间：
2023-06-01
影响因子：
8.9
通讯作者：
Yu, Philip S.
中科院分区：
文献类型：
--
作者：
Liu, Yixin;Jin, Ming;Yu, Philip S.
图上的深度学习最近引起了人们的极大兴趣。然而，大多数工作都集中在（半）监督学习，导致的缺点，包括标签依赖性强，泛化能力差，鲁棒性差。为了解决这些问题，自监督学习（SSL）通过精心设计的借口任务提取信息性知识，而不依赖于手动标签，已成为图形数据的一种有前途和趋势的学习范式。与计算机视觉和自然语言处理等其他领域的SSL不同，图上的SSL具有独特的背景，设计思想和分类法。在图自监督学习的保护伞下，我们对现有的采用SSL技术处理图数据的方法进行了及时而全面的回顾。我们构建了一个统一的框架，数学形式化的图形SSL的范例。根据任务的目的，我们将这些方法分为四类：基于生成的方法、基于辅助属性的方法、基于对比的方法和混合的方法。本文进一步描述了图SSL在各个研究领域的应用，总结了图SSL的常用数据集、评测基准、性能比较和开源代码。最后，我们讨论了在这一研究领域的剩余挑战和潜在的未来方向。
Deep learning on graphs has attracted significant interests recently. However, most of the works have focused on (semi-) supervised learning, resulting in shortcomings including heavy label reliance, poor generalization, and weak robustness. To address these issues, self-supervised learning (SSL), which extracts informative knowledge through well-designed pretext tasks without relying on manual labels, has become a promising and trending learning paradigm for graph data. Different from SSL on other domains like computer vision and natural language processing, SSL on graphs has an exclusive background, design ideas, and taxonomies. Under the umbrella of graph self-supervised learning, we present a timely and comprehensive review of the existing approaches which employ SSL techniques for graph data. We construct a unified framework that mathematically formalizes the paradigm of graph SSL. According to the objectives of pretext tasks, we divide these approaches into four categories: generation-based, auxiliary property-based, contrast-based, and hybrid approaches. We further describe the applications of graph SSL across various research fields and summarize the commonly used datasets, evaluation benchmark, performance comparison and open-source codes of graph SSL. Finally, we discuss the remaining challenges and potential future directions in this research field.