Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the I.I.D. hypothesis, i.e., testing and training graph data are independent and identically distributed. However, this I.I.D. hypothesis can hardly be satisfied in many real-world graph scenarios where the model performance substantially degrades when there exist distribution shifts between testing and training graph data. To solve this critical problem, out-of-distribution (OOD) generalization on graphs, which goes beyond the I.I.D. hypothesis, has made great progress and attracted ever-increasing attention from the research community. In this paper, we comprehensively survey OOD generalization on graphs and present a detailed review of recent advances in this area. First, we provide a formal problem definition of OOD generalization on graphs. Second, we categorize existing methods into three classes from conceptually different perspectives, i.e., data, model, and learning strategy, based on their positions in the graph machine learning pipeline, followed by detailed discussions for each category. We also review the theories related to OOD generalization on graphs and introduce the commonly used graph datasets for thorough evaluations. Last but not least, we share our insights on future research directions. This paper is the first systematic and comprehensive review of OOD generalization on graphs, to the best of our knowledge.
翻译:学术界和工业界都广泛研究了图象学。虽然大量新兴方法和技术正在兴旺发展,但大多数文献都建立在I.I.D.假设的基础上,即测试和培训图表数据是独立和同样分布的。然而,在许多真实的图表假设中,模型性能在测试和培训图数据之间存在分布变化时,很难满足,模型性能在实际世界图学假设中显著下降。为解决这一关键问题,图中除I.I.D.假设外的分布(OOOD)一般化(OOD)一般化(O.D.)一般化(O.D.)一般化(O.)一般化(O.D.)一般化(O.D.)一般化(O.D.)一般化(O.D.)一般化(O.D.)一般化(O.D.)一般化(O.)一般化(O.D.)一般化(O.D.)一般化(O.D.)一般化(O.D.D.D.)一般化(O.)一般化(O.D.D.)一般化(O.D.)一般化(O.)一般化(O.A.A.D.)一般化(O.A.)一般化(O.A.A.A.A.A.A.)一般化(O.I.D.I.I.I.)一般.)一般)一般化(O.A.A.A.A.A.A.A.A.A.A.A.A.)一般化(O.A.A.A.A.)一般化(O.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.A.)一般.)一般.)一般)和一般)一般的理论)一般分析)一般分析)一般分析)一般分析)一般分析)一般分析,我们使用)一般分析.A.