Table 1.
Symbols and definitions.
Fig 1.
Illustration of MCGCL.
Table 2.
The basic details of the datasets.
Table 3.
Results of joint test experiments for node classification.
Table 4.
Results of joint test experiments for link prediction.
Table 5.
Experimental results of momentum gradients.
Table 6.
Experimental results of candidate and evaluation.
Table 7.
Experimental results of node classification task on classical graph geural networks.
Table 8.
Experimental results of link prediction task on classical graph neural networks.
Fig 2.
Embedding visualization scatter plots.
From left to right are the embedded visualization scatter plots of clean graph, Metattack method, and MCGCL method, respectively.
Fig 3.
Embedding visualization scatter plots with different perturbation rates.
From left to right are the embedded visualization scatter plots with perturbation rates of 0.01, 0.05, and 0.1, respectively.