Порівняння методів

	Графові нейронні мережі	Вбудовування графів знань
Галузь	Мережевий аналіз	Мережевий аналіз
Родина	Process / pipeline	Machine learning
Рік появи	2017–2018 (major variants)	2013
Автор методу	—	Bordes, Usunier, García-Durán, Weston & Yakhnenko
Тип	Deep learning on graph-structured data	Graph representation learning via low-dimensional vector embeddings
Основоположне джерело	Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR).	Bordes, A., Usunier, N., García-Durán, A., Weston, J., & Yakhnenko, O. (2013). Translating embeddings for modeling multi-relational data. Advances in Neural Information Processing Systems, 26.
Інші назви	GNN, GCN, GAT, GraphSAGE	KG Embeddings, Knowledge Graph Representation Learning, Relational Embeddings, Bilgi Grafı Gömme
Пов'язані	5	3
Підсумок	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.	Knowledge Graph Embeddings (KGE) are a family of methods that represent entities and relations in a knowledge graph as dense, low-dimensional vectors in a continuous space. The foundational model, TransE, was introduced by Bordes, Usunier, García-Durán, Weston, and Yakhnenko in 2013. TransE treats each relation as a translation in embedding space — the head entity vector plus the relation vector should approximate the tail entity vector for any true triple (h, r, t). This simple geometric principle enabled effective link prediction and knowledge base completion at scale.