arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.09858cs.LGcs.AI
收藏

从因果视角看图机器学习分布外泛化综述

A Survey of Out-of-distribution Generalization for Graph Machine Learning from a Causal View

Case Western Reserve University(凯斯西储大学)

Jing Ma

AI总结:

本文从因果视角全面综述了图机器学习的分布外泛化问题,介绍了因果驱动方法如何通过探究数据生成与模型预测的因果机制提升泛化能力,并探讨了其在可信赖GML领域的应用与未来方向。

摘要:

图机器学习(GML)已成功应用于各种任务。然而,GML在分布外(OOD)数据上的泛化面临重大挑战,这引发了人们对其更广泛适用性的担忧。最新进展强调了因果驱动方法在克服这些泛化挑战中的关键作用。与主要依赖统计依赖性的传统GML方法不同,聚焦因果的策略深入探究数据生成和模型预测背后的潜在因果机制,从而显著提升了GML在不同环境中的泛化能力。本文全面回顾了涉及因果的GML泛化的最新进展。我们阐明了利用因果增强图模型泛化的基本概念,并对各种方法进行了分类,详细描述了它们的方法论及其相互联系。此外,我们探讨了因果在其他可信赖GML重要领域的融入,如解释性、公平性和鲁棒性。最后,本文讨论了潜在的未来研究方向,旨在阐述因果在增强图机器学习可信赖性方面的持续发展与未来潜力。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑