Methoden vergelijken
Bekijk de geselecteerde methoden naast elkaar; rijen die verschillen zijn gemarkeerd.
| Stochastic Block Model× | Graph Attention Network× | GraafNeuraal Netwerk× | |
|---|---|---|---|
| Vakgebied≠ | Netwerkanalyse | Deep learning | Deep learning |
| Familie≠ | Process / pipeline | Machine learning | Machine learning |
| Jaar van ontstaan≠ | 1983 | 2018 | 2017 |
| Grondlegger≠ | — | Veličković, P. et al. | Kipf, T.N. & Welling, M. |
| Type≠ | Probabilistic generative graph model | Graph neural network (attention-based) | Deep learning on graph-structured data |
| Oorspronkelijke bron≠ | Holland, P.W., Laskey, K.B. & Leinhardt, S. (1983). Stochastic Blockmodels: First Steps. Social Networks, 5(2), 109-137. DOI ↗ | Veličković, P. et al. (2018). Graph Attention Networks. ICLR. link ↗ | Kipf, T.N. & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. ICLR. link ↗ |
| Aliassen | SBM, degree-corrected SBM, DCSBM, Stokastik Blok Modeli (SBM) | Graf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network | Grafik Sinir Ağı (GNN), GNN, graph neural net, graph convolutional network |
| Verwant≠ | 7 | 4 | 4 |
| Samenvatting≠ | The Stochastic Block Model (SBM), introduced by Holland, Laskey and Leinhardt (1983), is a probabilistic generative model for graphs that assigns nodes to latent blocks and parametrically estimates the connection probabilities between blocks. It is the foundational approach for community detection, core-periphery identification, and hierarchical structure discovery in network analysis. | The Graph Attention Network (GAT), introduced by Veličković and colleagues in 2018, is a graph neural network variant that learns how much importance to assign to each neighbouring node through a self-attention mechanism. On heterogeneous neighbourhoods and relational classification it produces results superior to graph convolutional networks (GCN). | A Graph Neural Network (GNN) is a deep learning method, popularised by Kipf and Welling in 2017 with the Graph Convolutional Network, that learns from the relationships in network (graph) structures made of nodes and edges. It is designed for data that is naturally relational, such as social networks, molecular structures, and recommendation systems. |
| ScholarGateGegevensset ↗ |
|
|
|