id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_kcfnc6khsraxhcor4ocz3g7ixm	Ilya Makarov	Survey on graph embeddings and their applications to machine learning problems on graphs	2021	62	.pdf	application/pdf	30543	4088	59	embedding models based on matrix factorization, random-walks and deep learning machine learning problems on graphs, among which are node classification, link Keywords Graph embedding, Knowledge representation, Machine learning, Network science, Geometric deep learning, Graph neural networks, Node classification, Link prediction, high quality in relational machine learning tasks and constructing graph embeddings models (Lee et al., 2019) and graph neural networks (Wu et al., 2019b; Chen et al., 2018a; approaches to learn network embedding and introduce to a reader the core ideas of graph generalizing Node2vec (Grover & Leskovec, 2016) model to graph neural networks. Nowadays, many advanced deep neural network models are adapted to graph data. HSCA model, embedding homophily, network topological structure and node features dependency graph and learn node (word) embeddings using GCN. embedding models could really learn graph structure and its properties. embedding models for node classification, link prediction, node clustering and network Deep neural networks for learning graph representations.	./cache/work_kcfnc6khsraxhcor4ocz3g7ixm.pdf	./txt/work_kcfnc6khsraxhcor4ocz3g7ixm.txt