Susceptible-infected-spreading-based network embedding in static and temporal networks

EPJ Data Science

Table 2 AUC scores for link prediction. All the results shown are the average over 50 realizations. Bold indicates the optimal AUC among the embedding algorithms, ^∗ indicates the optimal AUC among all the algorithms. L2, L3, L4 are the short for link prediction metrics which counts the number of \(l=2,3,4\) paths, respectively

Dataset	DeepWalk	Node2Vec	CTDNE	tNodeEmbed	TSINE1	TSINE2	SINE	L2	L3	L4
HT2009	0.5209	0.5572	0.6038	0.5358	0.6740	0.6819	0.6726	0.7069^∗	0.7066	0.7055
ME	0.6439	0.6619	0.6575	0.7281	0.7329	0.7462	0.7744	0.7855	0.7878^∗	0.7790
Haggle	0.3823	0.7807	0.7796	\(\textbf{0.8702}^{*}\)	0.8051	0.8151	0.8267	0.8167	0.8255	0.8226
Fb-forum	0.5392	0.6882	0.6942	0.6013	0.7104	0.7195	\(\textbf{0.7302}^{*}\)	0.5606	0.7179	0.7203
DNC	0.5822	0.5933	0.7274	\(\textbf{0.9105}^{*}\)	0.7539	0.7529	0.7642	0.7704	0.7627	0.7193
CollegeMsg	0.5356	0.5454	0.7872	\(\textbf{0.8724}^{*}\)	0.8257	0.8321	0.8368	0.7176	0.8609	0.8203