Page 202 - 《软件学报》2026年第1期

刘子扬 等: 图对比学习方法综述 199

[80] Jiao YZ, Xiong Y, Zhang JW, Zhang Y, Zhang TQ, Zhu YY. Sub-graph contrast for scalable self-supervised graph representation
learning. In: Proc. of the 2020 IEEE Int’l Conf. on Data Mining. Sorrento: IEEE, 2020. 222–231. [doi: 10.1109/ICDM50108.2020.00031]
[81] Bielak P, Kajdanowicz T, Chawla NV. Graph Barlow twins: A self-supervised representation learning framework for graphs. Knowledge-
based Systems, 2022, 256: 109631. [doi: 10.1016/j.knosys.2022.109631]
[82] Li JC, Lu GQ, Li JC. A self-supervised graph autoencoder with Barlow twins. In: Proc. of the 19th Pacific Rim Int’l Conf. on Artificial
Intelligence. Shanghai: Springer, 2022. 501–512. [doi: 10.1007/978-3-031-20865-2_37]
[83] Jin M, Zheng YZ, Li YF, Gong C, Zhou C, Pan SR. Multi-scale contrastive siamese networks for self-supervised graph representation
learning. In: Proc. of the 13th Int’l Joint Conf. on Artificial Intelligence. 2021. 1477–1483. [doi: 10.24963/ijcai.2021/204]
[84] Zheng YZ, Pan SR, Lee VCS, Zheng Y, Yu PS. Rethinking and scaling up graph contrastive learning: An extremely efficient approach
with group discrimination. In: Proc. of the 36th Int’l Conf. on Neural Information Processing Systems. New Orleans: Curran Associates
Inc., 2022. 10809–10820.
[85] Chen D, Zhao X, Wang W, Tan Z, Xiao WD. Graph self-supervised learning with augmentation-aware contrastive learning. In: Proc. of
the 2023 ACM Web Conf. Austin: ACM, 2023. 154–164. [doi: 10.1145/3543507.3583246]
[86] Zhang HR, Wu QT, Yan JC, Wipf D, Yu PS. From canonical correlation analysis to self-supervised graph neural networks. In: Proc. of
the 35th Int’l Conf. on Neural Information Processing Systems. Curran Associates Inc., 2021. 76–89.

附中文参考文献
[55] 姚暄, 高君宇, 徐常胜. 基于自监督图对比学习的视频问答方法. 软件学报, 2023, 34(5): 2083–2100. http://www.jos.org.cn/1000-
9825/6775.htm [doi: 10.13328/j.cnki.jos.006775]

作者简介
刘子扬, 博士生, 主要研究领域为图机器学习, 推荐系统.
王朝坤, 博士, 副教授, 博士生导师, CCF 高级会员, 主要研究领域为数据库理论与系统, 图机器学习.
章衡, 博士, 副教授, CCF 专业会员, 主要研究领域为知识计算, 人工智能基础理论, 计算机科学逻辑.