arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.01440cs.LGcs.AIcs.SI
收藏

图上的少样本学习综述:从元学习到预训练与提示学习

A Survey of Few-Shot Learning on Graphs: from Meta-Learning to Pre-Training and Prompt Learning

Singapore Management University(新加坡管理大学);Zhejiang University(浙江大学);University of Science and Technology of China(中国科学技术大学)

Xingtong Yu, Yuan Fang, Zemin Liu, Yuxia Wu, Zhihao Wen, Jianyuan Bo, Xinming Zhang, Steven C. H. Hoi

AI总结:

本文综述了图上的少样本学习,系统分类了问题与技术,涵盖元学习、预训练及混合方法,并比较了各类方法的优劣,指出了未来研究方向。

摘要:

图表示学习是图中心任务中的关键步骤,已经取得了显著进展。早期技术通常在端到端设置下运行,严重依赖于充足标注数据的可用性。这一限制催生了图上的少样本学习,其中每个任务仅有少量标签可用。鉴于该领域文献众多,本综述致力于综合近期发展、提供比较性见解并指出未来方向。我们基于两大分类法系统性地对现有研究进行分类:(1)问题分类法,探讨不同类型的数据稀缺问题及其应用;(2)技术分类法,详细阐述解决这些数据稀缺少样本问题的关键策略。这些技术大致可分为元学习、预训练和混合方法,每个类别中都有更细粒度的分类,以帮助读者进行方法选择。在每个类别中,我们分析这些方法之间的关系,并比较它们的优势与局限。最后,我们概述了图上少样本学习的未来方向,以促进该领域的持续创新。本综述的网站可通过\url{https://github.com/smufang/fewshotgraph}访问。

英文摘要:

Graph representation learning, a critical step in graph-centric tasks, has seen significant advancements. Earlier techniques often operate in an end-to-end setting, which heavily rely on the availability of ample labeled data. This constraint has spurred the emergence of few-shot learning on graphs, where only a few labels are available for each task. Given the extensive literature in this field, this survey endeavors to synthesize recent developments, provide comparative insights, and identify future directions. We systematically categorize existing studies based on two major taxonomies: (1) Problem taxonomy, which explores different types of data scarcity problems and their applications, and (2) Technique taxonomy, which details key strategies for addressing these data-scarce few-shot problems. The techniques can be broadly categorized into meta-learning, pre-training, and hybrid approaches, with a finer-grained classification in each category to aid readers in their method selection process. Within each category, we analyze the relationships among these methods and compare their strengths and limitations. Finally, we outline prospective directions for few-shot learning on graphs to catalyze continued innovation in this field. The website for this survey can be accessed by \url{https://github.com/smufang/fewshotgraph}.

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。

↑