Porovnat metody

	Grafová neuronová síť	Analýza vícevrstvých sítí	Vnoření sítě
Obor	Analýza sítí	Analýza sítí	Analýza sítí
Rodina	Process / pipeline	Process / pipeline	Process / pipeline
Rok vzniku	2017–2018 (major variants)	2013–2014 (formal mathematical framework)	2014 (DeepWalk); 2016 (Node2Vec)
Tvůrce	—	Kivelä et al. (2014); De Domenico et al. (2013)	—
Typ	Deep learning on graph-structured data	Graph-theoretic network model	Representation learning / unsupervised network method
Původní zdroj	Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR).	Kivelä, M. et al. (2014). Multilayer Networks. Journal of Complex Networks, 2(3), 203–271.	Grover, A. & Leskovec, J. (2016). Node2Vec: Scalable Feature Learning for Networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 855-864.
Další názvy	GNN, GCN, GAT, GraphSAGE	multiplex network analysis, multiplex networks, Çok Katmanlı Ağ Analizi (Multiplex Networks)	node embedding, graph embedding, network representation learning, Ağ Gömme (Node2Vec, DeepWalk, LINE)
Příbuzné	5	6	3
Shrnutí	A Graph Neural Network (GNN) is a deep learning architecture that operates directly on graph-structured data by combining node features with structural information through iterative neighborhood message passing. The three canonical variants — the Graph Convolutional Network (GCN) introduced by Kipf and Welling in 2017, the Graph Attention Network (GAT) introduced by Veličković et al. in 2018, and GraphSAGE — differ in how they aggregate neighbor information: GCN applies a spectral convolution over the full adjacency, GAT weights neighbors by learned attention scores, and GraphSAGE samples and aggregates local neighborhoods inductively, enabling generalization to unseen nodes.	Multilayer network analysis is a graph-theoretic framework, formalised by Kivelä et al. (2014) and De Domenico et al. (2013), that represents the same set of nodes simultaneously across multiple relationship layers. Where a single-layer network collapses all relationships into one graph, the multilayer model preserves the distinct relational context of each layer — social platform, biological interaction type, or infrastructure tier — while also modelling how layers couple with each other through interlayer edges.	Network embedding is a family of representation-learning methods that map each node of a graph into a dense, low-dimensional vector while preserving the network's structural properties. The approach was formalised for social-network data by Perozzi, Al-Rfou, and Skiena with DeepWalk (2014), which adapted the Word2Vec skip-gram model to random walks on graphs, and extended by Grover and Leskovec with Node2Vec (2016), which introduced a biased random walk that balances breadth-first and depth-first exploration. These embeddings turn relational data into feature vectors that standard machine-learning classifiers and clustering algorithms can consume directly.