Comparer des méthodes
Examinez les méthodes sélectionnées côte à côte ; les lignes qui diffèrent sont mises en évidence.
| Réseau neuronal profond sur graphe faiblement supervisé× | Réseau neuronal graphique semi-supervisé× | |
|---|---|---|
| Domaine | Apprentissage profond | Apprentissage profond |
| Famille | Machine learning | Machine learning |
| Année d'origine≠ | 2017–2019 | 2017 (GCN formulation); 2004 (label propagation roots) |
| Auteur d'origine≠ | Derived from GNN literature (Scarselli et al. 2009; Kipf & Welling 2017) combined with weak supervision paradigm | Kipf, T. N. & Welling, M. (canonical formulation); Zhou et al. (label propagation precursor) |
| Type≠ | Graph-based deep learning with imperfect supervision | Semi-supervised graph representation learning |
| Source fondatrice≠ | Kipf, T. N., & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations (ICLR 2017). link ↗ | Kipf, T. N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR 2017). link ↗ |
| Alias | WS-GNN, graph neural network with weak supervision, noisy-label GNN, partially supervised GNN | Semi-supervised GNN, GNN semi-supervised learning, graph-based semi-supervised classification, semi-supervised node classification |
| Apparentées≠ | 6 | 4 |
| Résumé≠ | A Weakly Supervised Graph Neural Network (WS-GNN) is a graph deep-learning approach that learns from graph-structured data — nodes, edges, and their attributes — when only noisy, partial, or indirectly obtained labels are available. By coupling GNN message passing with noise-robust training strategies, it extends graph learning to real-world settings where clean, fully annotated graphs are scarce or expensive to obtain. | 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. |
| ScholarGateJeu de données ↗ |
|
|