arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.00904cs.LGcs.AI
收藏

图域自适应:挑战、进展与展望

Graph Domain Adaptation: Challenges, Progress and Prospects

Institute of Computing Technology, CAS(中国科学院计算技术研究所);University of Chinese Academy of Sciences(中国科学院大学)

Boshen Shi, Yongqing Wang, Fangda Guo, Bingbing Xu, Huawei Shen, Xueqi Cheng

AI总结:

本文首次系统综述了图域自适应(GDA)的研究现状、挑战、分类体系、代表性方法及未来展望,为图上跨域迁移学习提供了全面参考。

摘要:

由于图表示学习在实际应用中经常面临标签稀缺问题,研究者提出了图域自适应(Graph Domain Adaptation, GDA)作为一种跨图的有效知识迁移范式。具体而言,为了提升目标图上特定任务的模型性能,GDA 引入一组与任务相关的图作为源图,并将从源图学到的知识适配到目标图。由于 GDA 结合了图表示学习和域自适应的优势,它已成为图上迁移学习的一个有前景的方向,并在近年来吸引了越来越多的研究关注。本文对 GDA 的研究进行了全面综述,并详细介绍了近期进展。具体来说,我们概述了研究现状与挑战,提出了分类体系,介绍了代表性工作的细节,并讨论了未来展望。据我们所知,本文是第一篇关于图域自适应的综述。详细的论文列表可在 https://github.com/Skyorca/Awesome-Graph-Domain-Adaptation-Papers 获取。

英文摘要:

As graph representation learning often suffers from label scarcity problems in real-world applications, researchers have proposed graph domain adaptation (GDA) as an effective knowledge-transfer paradigm across graphs. In particular, to enhance model performance on target graphs with specific tasks, GDA introduces a bunch of task-related graphs as source graphs and adapts the knowledge learnt from source graphs to the target graphs. Since GDA combines the advantages of graph representation learning and domain adaptation, it has become a promising direction of transfer learning on graphs and has attracted an increasing amount of research interest in recent years. In this paper, we comprehensively overview the studies of GDA and present a detailed survey of recent advances. Specifically, we outline the research status and challenges, propose a taxonomy, introduce the details of representative works, and discuss the prospects. To the best of our knowledge, this paper is the first survey for graph domain adaptation. A detailed paper list is available at https://github.com/Skyorca/Awesome-Graph-Domain-Adaptation-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。

↑