图对比学习综述  

A Survey on Graph Contrastive Learning

作　　者：岑科廷 沈华伟[1,2] 曹婍 程学旗 CEN Keting;SHEN Huawei;CAO Qi;CHENG Xueqi(Data Intelligence System Research Center,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;University of Chinese Academy of Sciences,Beijing 101408,China;CAS Key Laboratory of Network Data Science and Technology,Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China)

机构地区：[1]中国科学院计算技术研究所数据智能系统研究中心,北京100190 [2]中国科学院大学,北京101408 [3]中国科学院计算技术研究所网络数据科学与技术重点实验室,北京100190

出　　处：《中文信息学报》2023年第5期1-21,共21页Journal of Chinese Information Processing

基　　金：国家重点研发计划(2018YFC0825204);国家自然科学基金(62102402,91746301);北京智源青年科学家项目(BAAI2019QN0304)。

摘　　要：对比学习作为一种自监督式的深度学习范式,在计算机视觉、自然语言处理等领域取得了瞩目的成绩。受这些成功的对比学习模型的启发,近年来大量研究者尝试将其拓展到图数据上,这为推动图对比学习的发展提供了坚实的基础。该领域现有的综述主要关注于传统的图自监督学习任务,而缺少对图对比学习方法的梳理和归纳。为了更好地帮助相关领域的研究者,该文梳理了近些年来的图对比学习模型,通过将现有工作归纳到一个统一的框架下,突出其发展脉络。最后该文总结了图对比学习常用的数据集和评价指标,并展望了该领域未来的发展方向。As a self-supervised deep learning paradigm,contrastive learning has achieved remarkable results in computer vision and natural language processing.Inspired by the success of contrastive learning in these fields,researchers have tried to extend it to graph data and promoted the development of graph contrastive learning.To provide a comprehensive overview of graph contrastive learning,this paper summarizes recent works under a unified framework to highlight the development trends.It also catalogues the popular datasets and evaluation metrics for graph contrastive learning,and concludes with the possible future direction of the field.

关 键 词：自监督学习 图对比学习 图表示学习 预训练 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]