Сравнение методов

	Распространение меток	Графовая нейронная сеть	Спектральная кластеризация
Область	Машинное обучение	Сетевой анализ	Машинное обучение
Семейство	Machine learning	Process / pipeline	Machine learning
Год появления	2002	2017–2018 (major variants)	2002
Автор метода	Zhu, X. & Ghahramani, Z.	—	Ng, A. Y.; Jordan, M. I.; Weiss, Y.
Тип	Graph-based semi-supervised classification	Deep learning on graph-structured data	Graph-based clustering (spectral method)
Основополагающий источник	Zhu, X., & Ghahramani, Z. (2002). Learning from labeled and unlabeled data with label propagation. Technical Report CMU-CALD-02-107, Carnegie Mellon University.	Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR).	Ng, A. Y., Jordan, M. I., & Weiss, Y. (2002). On Spectral Clustering: Analysis and an Algorithm. Advances in Neural Information Processing Systems, 14, 849–856.
Другие названия	LP, label spreading, graph-based semi-supervised learning, harmonic label propagation	GNN, GCN, GAT, GraphSAGE	NJW spectral clustering, graph Laplacian clustering, normalized spectral clustering, spectral graph clustering
Связанные	3	5	5
Сводка	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.	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.	Spectral Clustering is a graph-based unsupervised learning algorithm, formalized by Ng, Jordan, and Weiss in 2002, that maps data points into a low-dimensional eigenspace derived from the similarity graph's Laplacian before applying k-means. This spectral embedding makes it possible to recover clusters of arbitrary shape — rings, crescents, interleaved spirals — that Euclidean distance-based methods consistently fail to separate.