Fig. 1From: Co-MLHAN: contrastive learning for multilayer heterogeneous attributed networksIllustration of a multilayer heterogeneous attributed graph with two layers (\(G_{l}\) and \(G_{l'}\)), three types of nodes (M (movie)–A (actor)–D (director)), and different content features for different nodes (e.g., text, images, structured attributes)Back to article page