השוואת שיטות

	שיכוני גרפי ידע	רשתות נוירונים גרפיות
תחום	ניתוח רשתות	ניתוח רשתות
משפחה	Machine learning	Process / pipeline
שנת המקור	2013	2017–2018 (major variants)
הוגה השיטה	Bordes, Usunier, García-Durán, Weston & Yakhnenko	—
סוג	Graph representation learning via low-dimensional vector embeddings	Deep learning on graph-structured data
מקור מכונן	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.	Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR).
כינויים	KG Embeddings, Knowledge Graph Representation Learning, Relational Embeddings, Bilgi Grafı Gömme	GNN, GCN, GAT, GraphSAGE
קשורות	3	5
תקציר	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.	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.