Comparer des méthodes

	Réseau de neurones à graphes	Classification d'images par CNN	XGBoost
Domaine	Apprentissage profond	Apprentissage profond	Apprentissage automatique
Famille	Machine learning	Machine learning	Machine learning
Année d'origine	2017	2016	2016
Auteur d'origine	Kipf, T.N. & Welling, M.	He, K. et al. (ResNet); Tan, M. & Le, Q.V. (EfficientNet)	Chen, T. & Guestrin, C.
Type	Deep learning on graph-structured data	Deep convolutional neural network (supervised)	Ensemble (gradient-boosted decision trees)
Source fondatrice	Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. ICLR.	He, K., Zhang, X., Ren, S. & Sun, J. (2016). Deep Residual Learning for Image Recognition. CVPR.	Chen, T. & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD, 785–794.
Alias	Grafik Sinir Ağı (GNN), GNN, graph neural net, graph convolutional network	CNN — Görüntü Sınıflandırma (ResNet / VGG / EfficientNet), convolutional neural network image classifier, deep image classification, ResNet / VGG / EfficientNet	XGBoost, extreme gradient boosting, scalable tree boosting
Apparentées	4	5	5
Résumé	A Graph Neural Network (GNN) is a deep learning method, popularised by Kipf and Welling in 2017 with the Graph Convolutional Network, that learns from the relationships in network (graph) structures made of nodes and edges. It is designed for data that is naturally relational, such as social networks, molecular structures, and recommendation systems.	CNN image classification uses deep convolutional architectures such as ResNet (He et al., 2016), VGG and EfficientNet (Tan & Le, 2019) to sort images into categories. Stacked convolutional layers learn a hierarchy of visual features directly from pixels, and skip (residual) connections prevent the vanishing-gradient problem in very deep networks.	XGBoost (Extreme Gradient Boosting) is a scalable tree-boosting algorithm introduced by Tianqi Chen and Carlos Guestrin in 2016. It builds a strong predictor by adding decision trees one at a time, each correcting the errors left by the trees before it, and is a powerful prediction method widely used in competitions.