Salīdzināt metodes
Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.
| Daļēji uzraudzīts grafu neironu tīkls× | Daudzpusīgā apguve× | |
|---|---|---|
| Nozare≠ | Dziļā mācīšanās | Mašīnmācīšanās |
| Saime | Machine learning | Machine learning |
| Izcelsmes gads≠ | 2017 (GCN formulation); 2004 (label propagation roots) | 1970s–2006 (formalized) |
| Autors≠ | Kipf, T. N. & Welling, M. (canonical formulation); Zhou et al. (label propagation precursor) | Vapnik, V. N. and others (community of researchers, 1970s–2000s) |
| Tips≠ | Semi-supervised graph representation learning | Learning paradigm |
| Pirmavots≠ | Kipf, T. N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR 2017). link ↗ | Chapelle, O., Scholkopf, B., & Zien, A. (Eds.) (2006). Semi-Supervised Learning. MIT Press. ISBN: 978-0-262-03358-9 |
| Citi nosaukumi | Semi-supervised GNN, GNN semi-supervised learning, graph-based semi-supervised classification, semi-supervised node classification | SSL, semi-supervised machine learning, transductive learning, label-efficient learning |
| Saistītās≠ | 4 | 5 |
| Kopsavilkums≠ | A semi-supervised graph neural network trains a GNN on a graph where only a small fraction of nodes carry labels, using neighborhood message-passing to spread information from labeled nodes to unlabeled ones. The approach, popularised by Kipf and Welling's 2017 Graph Convolutional Network, achieves strong node-classification accuracy even when labeled examples are scarce. | Semi-supervised learning (SSL) is a machine learning paradigm that trains models using a small set of labeled examples together with a much larger pool of unlabeled data. By leveraging the structure inherent in unlabeled data, SSL achieves accuracy closer to fully supervised models while requiring far fewer costly manual labels — making it practical when labeling is expensive, slow, or resource-constrained. |
| ScholarGateDatu kopa ↗ |
|
|