Сравнение методов

	Semi-supervised Graph Neural Network	Распространение меток
Область	Глубокое обучение	Машинное обучение
Семейство	Machine learning	Machine learning
Год появления	2017 (GCN formulation); 2004 (label propagation roots)	2002
Автор метода	Kipf, T. N. & Welling, M. (canonical formulation); Zhou et al. (label propagation precursor)	Zhu, X. & Ghahramani, Z.
Тип	Semi-supervised graph representation learning	Graph-based semi-supervised classification
Основополагающий источник	Kipf, T. N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR 2017).	Zhu, X., & Ghahramani, Z. (2002). Learning from labeled and unlabeled data with label propagation. Technical Report CMU-CALD-02-107, Carnegie Mellon University.
Другие названия	Semi-supervised GNN, GNN semi-supervised learning, graph-based semi-supervised classification, semi-supervised node classification	LP, label spreading, graph-based semi-supervised learning, harmonic label propagation
Связанные	4	3
Сводка	A semi-supervised graph neural network trains a GNN on a graph where only a small fraction of nodes carry labels, using neighborhood message-passing to spread information from labeled nodes to unlabeled ones. The approach, popularised by Kipf and Welling's 2017 Graph Convolutional Network, achieves strong node-classification accuracy even when labeled examples are scarce.	Label Propagation is a graph-based semi-supervised learning algorithm introduced by Zhu and Ghahramani in 2002 that spreads class labels from a small set of labeled nodes to a large set of unlabeled nodes by iteratively diffusing label information along the edges of a similarity graph, exploiting the manifold structure of the data.