Bitcoin-Alpha, Bitcoin-OTC, WikiRfA: https://snap.stanford.edu/data
Slahsdot, Epinions: https://www.aminer.cn/data-sna
Dimensionality of embedding = 128
SNE [PAKDD'17]
Learning rate = 0.025
Number of samples to train = 10 Million
Window size = 2
Maximum length of random walk path = 40
Number of random walks starting at each node = 20
SIDE [WWW'18]
Learning rate = 0.025
Window size = 5
Maximum length of random walk path = 40
Number of random walks starting at each node = 80
SGCN [ICDM'18]
Learning rate = 0.5
Number of layers = 2
Loss2 regularization = 5
SLF [KDD'19]
Learning rate = 0.025
Sample size of the null relationships = 10 (for Bitcoin-OTC, Epinions), 20 (for Bitcoin-Alpha, WikiRfA, Slashdot)
Initialization parameter for the logistic activation function (i.e., p0) = 0.001
ASiNE (Ours)
Learning rate = 0.01
Size of generating and discriminating edges = 20
Number of iterations for generators and discriminators per epoch = 10
Window size = 2