Comparer des méthodes

	Réseau de neurones convolutifs sur graphes (GCN)	Réseau d'attention sur graphe
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2017	2018
Auteur d'origine	Kipf, T. N. & Welling, M.	Veličković, P. et al.
Type	Spectral graph neural network (semi-supervised node classification)	Graph neural network (attention-based)
Source fondatrice	Kipf, T. N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. Proceedings of the 5th International Conference on Learning Representations (ICLR 2017), Toulon, France.	Veličković, P. et al. (2018). Graph Attention Networks. ICLR.
Alias	GCN, graph convolutional network, spectral graph convolution, Kipf-Welling GCN	Graf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network
Apparentées	1	4
Résumé	Graph Convolutional Network (GCN) is a foundational deep learning architecture for graph-structured data, introduced by Thomas N. Kipf and Max Welling at ICLR 2017. It extends the convolution operation to irregular graph domains via a first-order spectral approximation, enabling each node to aggregate feature information from its neighbors. The model became the canonical baseline for semi-supervised node classification and sparked the modern graph neural network research agenda.	The Graph Attention Network (GAT), introduced by Veličković and colleagues in 2018, is a graph neural network variant that learns how much importance to assign to each neighbouring node through a self-attention mechanism. On heterogeneous neighbourhoods and relational classification it produces results superior to graph convolutional networks (GCN).