Comparer des méthodes

	Réseau neuronal profond sur graphe faiblement supervisé	Réseau neuronal à graphes
Domaine	Apprentissage profond	Analyse de réseaux
Famille	Machine learning	Process / pipeline
Année d'origine	2017–2019	2017–2018 (major variants)
Auteur d'origine	Derived from GNN literature (Scarselli et al. 2009; Kipf & Welling 2017) combined with weak supervision paradigm	—
Type	Graph-based deep learning with imperfect supervision	Deep learning on graph-structured data
Source fondatrice	Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations (ICLR 2017).	Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR).
Alias	WS-GNN, graph neural network with weak supervision, noisy-label GNN, partially supervised GNN	GNN, GCN, GAT, GraphSAGE
Apparentées	6	5
Résumé	A Weakly Supervised Graph Neural Network (WS-GNN) is a graph deep-learning approach that learns from graph-structured data — nodes, edges, and their attributes — when only noisy, partial, or indirectly obtained labels are available. By coupling GNN message passing with noise-robust training strategies, it extends graph learning to real-world settings where clean, fully annotated graphs are scarce or expensive to obtain.	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.