Skip to main content
Figure 4 | EPJ Data Science

Figure 4

From: Predicting partially observed processes on temporal networks by Dynamics-Aware Node Embeddings (DyANE)

Figure 4

Scatterplots of the final predicted epidemic size (number of infectious and recovered nodes at the end of the data set), vs. the real one. Each point corresponds to one simulation, and we vary the epidemic parameters in order to scan a wide range of outcomes. Here we use the dyn-supra + DeepWalk method. The Pearson correlation coefficients for the predicted vs. real sizes are 0.957 for InVS15, 0.88 for LH10, 0.98 for SFHH, 0.96 for Thiers13 and 0.95 for LyonSchool

Back to article page