Compara mètodes

	Xarxa Neuronal de Grafs	Classificació d'imatges amb CNN	Màquina de Vectors de Suport (Classificació)
Camp	Aprenentatge profund	Aprenentatge profund	Aprenentatge automàtic
Família	Machine learning	Machine learning	Machine learning
Any d'origen	2017	2016	1995
Autor original	Kipf, T.N. & Welling, M.	He, K. et al. (ResNet); Tan, M. & Le, Q.V. (EfficientNet)	Cortes, C. & Vapnik, V.
Tipus	Deep learning on graph-structured data	Deep convolutional neural network (supervised)	Maximum-margin classifier (kernel method)
Font seminal	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.	Cortes, C. & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20, 273–297.
Àlies	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	Destek Vektör Makinesi (SVM — Sınıflandırma), support-vector network, SVM classifier, maximum-margin classifier
Relacionats	4	5	5
Resum	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.	The Support Vector Machine, introduced by Corinna Cortes and Vladimir Vapnik in 1995, is a classifier that finds the optimal separating hyperplane between classes in a high-dimensional space. It chooses the boundary that leaves the widest possible margin to the nearest training points, which makes its decisions robust on new data.