Σύγκριση μεθόδων

	Πρόβλεψη Συνδέσεων	Ανίχνευση Κοινοτήτων	Γραφικά Νευρωνικά Δίκτυα	Ενσωμάτωση Δικτύου
Πεδίο	Ανάλυση Δικτύων	Ανάλυση Δικτύων	Ανάλυση Δικτύων	Ανάλυση Δικτύων
Οικογένεια	Process / pipeline	Process / pipeline	Process / pipeline	Process / pipeline
Έτος προέλευσης	2003	2002–2019 (algorithm family)	2017–2018 (major variants)	2014 (DeepWalk); 2016 (Node2Vec)
Δημιουργός	—	Louvain: Blondel et al. (2008); Leiden: Traag et al. (2019); Girvan-Newman: Girvan & Newman (2002); Infomap: Rosvall & Bergstrom (2008)	—	—
Τύπος	Network inference task	Graph-partitioning / clustering algorithm family	Deep learning on graph-structured data	Representation learning / unsupervised network method
Θεμελιώδης πηγή	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.	Blondel, V.D., Guillaume, J.-L., Lambiotte, R. & Lefebvre, E. (2008). Fast Unfolding of Communities in Large Networks. Journal of Statistical Mechanics, 2008(10), P10008.	Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR).	Grover, A. & Leskovec, J. (2016). Node2Vec: Scalable Feature Learning for Networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD), 855-864.
Εναλλακτικές ονομασίες	Bağlantı Tahmini (Link Prediction), missing link prediction, future link prediction, edge prediction	graph clustering, network partitioning, Topluluk Tespiti (Louvain, Girvan-Newman, Leiden)	GNN, GCN, GAT, GraphSAGE	node embedding, graph embedding, network representation learning, Ağ Gömme (Node2Vec, DeepWalk, LINE)
Συναφείς	5	5	5	3
Σύνοψη	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.	Community detection is a family of graph-partitioning algorithms that discover densely connected sub-groups — communities — within a network. First formalised through the modularity measure by Girvan and Newman (2002), the field advanced rapidly with the Louvain method (Blondel et al., 2008), the Leiden refinement (Traag et al., 2019), and the information-theoretic Infomap approach. All variants answer the same question: which nodes cluster together more tightly among themselves than with the rest of the network?	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.	Network embedding is a family of representation-learning methods that map each node of a graph into a dense, low-dimensional vector while preserving the network's structural properties. The approach was formalised for social-network data by Perozzi, Al-Rfou, and Skiena with DeepWalk (2014), which adapted the Word2Vec skip-gram model to random walks on graphs, and extended by Grover and Leskovec with Node2Vec (2016), which introduced a biased random walk that balances breadth-first and depth-first exploration. These embeddings turn relational data into feature vectors that standard machine-learning classifiers and clustering algorithms can consume directly.