arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.11153cs.LG
收藏

超越泛化:图上分布外适应综述

Beyond Generalization: A Survey of Out-Of-Distribution Adaptation on Graphs

Northwestern University(西北大学)

Shuhan Liu, Kaize Ding

AI总结:

本文综述了图分布外适应方法,涵盖训练时和测试时两大场景,系统分类现有方法并探讨其技术,最后指出未来研究方向与挑战。

摘要:

图上的分布偏移——图机器学习模型训练与测试时的数据分布差异,在现实场景中通常无处不在且不可避免。这种偏移可能严重恶化模型性能,为可靠的图机器学习带来重大挑战。因此,旨在缓解分布偏移并将知识从一种分布适应到另一种分布的图分布外(OOD)适应方法的研究激增。在我们的综述中,我们对图OOD适应方法进行了最新且具有前瞻性的回顾,涵盖训练时和测试时图OOD适应两个主要问题场景。我们首先正式地阐述这两个问题,然后讨论图上不同类型的分布偏移。基于我们提出的图OOD适应分类法,我们根据现有方法的学习范式对其进行系统分类,并探讨其背后的技术。最后,我们指出了有前景的研究方向及相应挑战。我们还在https://github.com/kaize0409/Awesome-Graph-OOD-Adaptation.git提供了持续更新的阅读列表。

英文摘要:

Distribution shifts on graphs -- the data distribution discrepancies between training and testing a graph machine learning model, are often ubiquitous and unavoidable in real-world scenarios. Such shifts may severely deteriorate the performance of the model, posing significant challenges for reliable graph machine learning. Consequently, there has been a surge in research on graph Out-Of-Distribution (OOD) adaptation methods that aim to mitigate the distribution shifts and adapt the knowledge from one distribution to another. In our survey, we provide an up-to-date and forward-looking review of graph OOD adaptation methods, covering two main problem scenarios including training-time as well as test-time graph OOD adaptation. We start by formally formulating the two problems and then discuss different types of distribution shifts on graphs. Based on our proposed taxonomy for graph OOD adaptation, we systematically categorize the existing methods according to their learning paradigm and investigate the techniques behind them. Finally, we point out promising research directions and the corresponding challenges. We also provide a continuously updated reading list at https://github.com/kaize0409/Awesome-Graph-OOD-Adaptation.git

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。

↑