Figure 8From: Predicting partially observed processes on temporal networks by Dynamics-Aware Node Embeddings (DyANE)Effect of the variations in the supra-adjacency representation, for the DeepWalk embedding. Here \((\beta , \mu ) = (0.13, 0.055)\). Top: effect of using undirected edges. Bottom: effect of introducing weights depending on time difference. Bars indicate the standard deviationBack to article page