基于无负样本损失和自适应增强的图对比学习

周天琪,杨艳,张继杰,殷少伟,郭增强

Graph contrastive learning based on negative-sample-free loss and adaptive augmentation

Tian-qi ZHOU,Yan YANG,Ji-jie ZHANG,Shao-wei YIN,Zeng-qiang GUO

表 4 不同对比方法的内存占用和运行时间设置

Tab.4 Memory usage and runtime settings of different comparison methods

模型 Cora数据集 Citeseer数据集 ${\rm{MB}}$ $S$ ${\rm{MB}}$ $S$ DGI 1257 60.16 1053 76.27 GMI 1078 472.52 1411 631.41 GRACE 777 60.93 1151 163.54 GCA 845 805.99 1093 1207.03 GNSA 651 28.59 885 15.13