An Empirical Study of Graph Contrastive Learning | |
Zhu, Yanqiao1,2; Xu, Yichen3; Liu, Qiang1,2; Wu, Shu1,2 | |
2021-12 | |
会议名称 | The 35th Conference on Neural Information Processing Systems (NeurIPS 2021) |
卷号 | 1 |
会议日期 | 2021-12 |
会议地点 | Online |
出版者 | Curran Associates, Inc. |
摘要 | Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph representations without human annotations. Although remarkable progress has been witnessed recently, the success behind GCL is still left somewhat mysterious. In this work, we first identify several critical design considerations within a general GCL paradigm, including augmentation functions, contrasting modes, contrastive objectives, and negative mining techniques. Then, to understand the interplay of different GCL components, we conduct extensive, controlled experiments over a set of benchmark tasks on datasets across various domains. Our empirical studies suggest a set of general receipts for effective GCL, e.g., simple topology augmentations that produce sparse graph views bring promising performance improvements; contrasting modes should be aligned with the granularities of end tasks. In addition, to foster future research and ease the implementation of GCL algorithms, we develop an easy-to-use library PyGCL, featuring modularized CL components, standardized evaluation, and experiment management. We envision this work to provide useful empirical evidence of effective GCL algorithms and offer several insights for future research. |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48471 |
专题 | 智能感知与计算研究中心 |
通讯作者 | Wu, Shu |
作者单位 | 1.Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, University of Chinese Academy of Sciences 3.School of Computer Science, Beijing University of Posts and Telecommunications |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Zhu, Yanqiao,Xu, Yichen,Liu, Qiang,et al. An Empirical Study of Graph Contrastive Learning[C]:Curran Associates, Inc.,2021. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
neurips_2021.pdf(475KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论