arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2202.08871cs.LG
收藏

图机器学习中的图数据增强研究综述

Graph Data Augmentation for Graph Machine Learning: A Survey

Snap Inc.(Snap公司);University of Notre Dame(圣母大学);Michigan State University(密歇根州立大学);Cornell University(康奈尔大学);Technical University of Munich(慕尼黑工业大学)

Tong Zhao, Wei Jin, Yozen Liu, Yingheng Wang, Gang Liu, Stephan Günnemann, Neil Shah, Meng Jiang

摘要:

数据增强最近在图机器学习中引起了越来越多的兴趣,因为它被证明能够通过添加训练数据来提高模型性能和泛化能力。尽管最近出现了这种激增,但由于图数据的复杂非欧几里德结构带来的挑战,该领域仍然相对未被充分探索,这限制了对其他类型的图像,视频或文本数据的传统增强操作的直接类比。我们的工作的目的是给现有的图形数据增强方法的必要和及时的概述,值得注意的是,我们提出了一个全面和系统的调查图数据增强的方法,总结文献结构化的方式。我们首先介绍了三种不同的分类法,分别从数据,任务和学习的角度对图数据增强方法进行分类。接下来,我们将介绍图数据增强的最新进展,按其方法和应用区分。最后,我们概述了目前未解决的挑战和未来的研究方向。总的来说,我们的工作旨在澄清图数据增强的现有文献的情况,并激励在这一领域的额外工作,为更广泛的图机器学习领域的研究人员和从业人员提供有用的资源。此外,我们在https://github.com/zhao-tong/graph-data-augmentation-papers上提供了一个不断更新的阅读清单。

英文摘要:

Data augmentation has recently seen increased interest in graph machine learning given its demonstrated ability to improve model performance and generalization by added training data. Despite this recent surge, the area is still relatively under-explored, due to the challenges brought by complex, non-Euclidean structure of graph data, which limits the direct analogizing of traditional augmentation operations on other types of image, video or text data. Our work aims to give a necessary and timely overview of existing graph data augmentation methods; notably, we present a comprehensive and systematic survey of graph data augmentation approaches, summarizing the literature in a structured manner. We first introduce three different taxonomies for categorizing graph data augmentation methods from the data, task, and learning perspectives, respectively. Next, we introduce recent advances in graph data augmentation, differentiated by their methodologies and applications. We conclude by outlining currently unsolved challenges and directions for future research. Overall, our work aims to clarify the landscape of existing literature in graph data augmentation and motivates additional work in this area, providing a helpful resource for researchers and practitioners in the broader graph machine learning domain. Additionally, we provide a continuously updated reading list at https://github.com/zhao-tong/graph-data-augmentation-papers.

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。

↑