从因果视角梳理图机器学习的分布外泛化研究进展
A Survey of Out-of-distribution Generalization for Graph Machine Learning from a Causal View
- 提出用因果机制替代统计相关性来提升模型泛化能力
- 系统分类了基于因果的图学习方法及其关联
- 适合关注可信图学习与模型鲁棒性的研究者
图机器学习（GML）已在诸多任务中取得成功，但其在分布外（OOD）数据上的泛化能力仍面临重大挑战，限制了实际应用。近期研究表明，基于因果的方法在解决此类泛化问题中起关键作用。与依赖统计依赖的传统GML方法不同，因果驱动策略深入挖掘数据生成和模型预测背后的因果机制，显著提升了GML在不同环境中的泛化性能。本文全面回顾了近年来因果驱动的图学习泛化研究进展，阐明了利用因果提升图模型泛化的基本概念，对各类方法进行系统分类，并详细描述其技术路径与内在联系。此外，还探讨了因果性在可解释性、公平性和鲁棒性等可信图学习相关领域中的应用。最后，讨论了未来潜在的研究方向，旨在推动因果方法在提升图机器学习可信度方面的持续发展与潜力。
原文摘要 · Abstract (English)
Graph machine learning (GML) has been successfully applied across a wide range of tasks. Nonetheless, GML faces significant challenges in generalizing over out-of-distribution (OOD) data, which raises concerns about its wider applicability. Recent advancements have underscored the crucial role of causality-driven approaches in overcoming these generalization challenges. Distinct from traditional GML methods that primarily rely on statistical dependencies, causality-focused strategies delve into the underlying causal mechanisms of data generation and model prediction, thus significantly improving the generalization of GML across different environments. This paper offers a thorough review of recent progress in causality-involved GML generalization. We elucidate the fundamental concepts of employing causality to enhance graph model generalization and categorize the various approaches, providing detailed descriptions of their methodologies and the connections among them. Furthermore, we explore the incorporation of causality in other related important areas of trustworthy GML, such as explanation, fairness, and robustness. Concluding with a discussion on potential future research directions, this review seeks to articulate the continuing development and future potential of causality in enhancing the trustworthiness of graph machine learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。