An adversarial learning approach for discovering social relations in human-centered information networks

EURASIP Journal on Wireless Communications and Networking

Table 2 Micro- F₁ and Macro- F₁ scores on CitNet dataset in link prediction (α=0.1,β=0.1)

%Training edges	10%		30%		50%		70%		90%
	Micro- F₁	Macro- F₁	Micro- F₁	Macro- F₁	Micro- F₁	Macro- F₁	Micro- F₁	Macro- F₁	Micro- F₁	Macro- F₁
GAN	0.7734	0.7722	0.7714	0.7703	0.7725	0.7713	0.7715	0.7704	0.7718	0.7707
LSGAN	0.8124	0.8085	0.8130	0.8092	0.8109	0.8071	0.8120	0.8083	0.8114	0.8076
DeepWalk	0.6041	0.3766	0.6041	0.3766	0.6041	0.3766	0.6041	0.3766	0.6041	0.3766
node2vec	0.6041	0.3766	0.6041	0.3766	0.6041	0.3766	0.6041	0.3766	0.6041	0.3766
AIDW	0.6043	0.3775	0.6043	0.3775	0.6043	0.3776	0.6043	0.3774	0.6043	0.3775
Jaccard	0.6050	0.3792	0.6050	0.3792	0.6050	0.3792	0.6050	0.3792	0.6050	0.3792
CosSim	0.3990	0.2897	0.3990	0.2897	0.3990	0.2897	0.3990	0.2897	0.3990	0.2897
SRGAN	0.8328	0.8248	0.8325	0.8248	0.8335	0.8259	0.8337	0.8261	0.8340	0.8265