Сравнение методов

	Визуальное контрастивное обучение	Графовая сеть внимания (Graph Attention Network, GAT)
Область	Глубокое обучение	Глубокое обучение
Семейство	Machine learning	Machine learning
Год появления	2020	2018
Автор метода	Chen, T. et al. (SimCLR); He, K. et al. (MoCo)	Veličković, P. et al.
Тип	Self-supervised deep representation learning	Graph neural network (attention-based)
Основополагающий источник	Chen, T., Kornblith, S., Norouzi, M. & Hinton, G. (2020). A Simple Framework for Contrastive Learning of Visual Representations. ICML.	Veličković, P. et al. (2018). Graph Attention Networks. ICLR.
Другие названия	Karşıtlık Öğrenmesi — Görsel (SimCLR / MoCo / BYOL), contrastive learning, self-supervised visual representation learning, SimCLR	Graf Dikkat Ağı (GAT), GAT, graph attention network, attention-based graph neural network
Связанные	5	4
Сводка	Visual contrastive learning is a self-supervised deep-learning approach — popularised by frameworks such as SimCLR (Chen et al., 2020) and MoCo (He et al., 2020) — that learns rich image representations without labels by pulling different augmentations of the same image together and pushing different images apart. It turns a large pool of unlabelled images into a useful feature extractor.	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).