手法を比較

	ネットワークにおける欠損および将来のエッジ推論	グラフニューラルネットワーク
分野	ネットワーク分析	ネットワーク分析
系統	Process / pipeline	Process / pipeline
提唱年	2003	2017–2018 (major variants)
提唱者	—	—
種類	Network inference task	Deep learning on graph-structured data
原典	Liben-Nowell, D. & Kleinberg, J. (2007). The Link-Prediction Problem for Social Networks. Journal of the American Society for Information Science and Technology, 58(7), 1019-1031.	Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR).
別名	Bağlantı Tahmini (Link Prediction), missing link prediction, future link prediction, edge prediction	GNN, GCN, GAT, GraphSAGE
関連	5	5
概要	Link prediction is a network-analysis task that estimates which edges are missing from an observed graph or which edges are likely to form in the future. Formalised by Liben-Nowell and Kleinberg (2003, 2007), it covers a spectrum of approaches — from simple structural similarity indices such as Common Neighbors, Jaccard coefficient, and Adamic-Adar, to matrix factorisation, and graph neural network (GNN) methods — and is evaluated with AUC and Average Precision to account for the heavily imbalanced ratio of real to non-existing edges.	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.