Salīdzināt metodes

	Vāji uzraudzīts grafu neironu tīkls	Vāji uzraudzīts Transformers
Nozare	Dziļā mācīšanās	Dziļā mācīšanās
Saime	Machine learning	Machine learning
Izcelsmes gads	2017–2019	2017–2019
Autors	Derived from GNN literature (Scarselli et al. 2009; Kipf & Welling 2017) combined with weak supervision paradigm	Multiple contributors (weak supervision paradigm: Zhou 2018; transformer backbone: Vaswani et al. 2017)
Tips	Graph-based deep learning with imperfect supervision	Weakly supervised deep learning
Pirmavots	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).	Ratner, A., Bach, S. H., Ehrenberg, H., Fries, J., Wu, S., & Re, C. (2017). Snorkel: Rapid training data creation with weak supervision. Proceedings of the VLDB Endowment, 11(3), 269–282.
Citi nosaukumi	WS-GNN, graph neural network with weak supervision, noisy-label GNN, partially supervised GNN	WST, weakly supervised attention model, noisy-label transformer, weak supervision with transformers
Saistītās	6	5
Kopsavilkums	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.	Weakly Supervised Transformer combines the representational power of Transformer architectures with weak supervision strategies that exploit noisy, incomplete, or programmatically generated labels — making it possible to train high-quality NLP and vision models when fully annotated datasets are scarce or prohibitively expensive to produce.