id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
cord-024437-r5wnz7rq	Wang, Yubin	SLGAT: Soft Labels Guided Graph Attention Networks	2020-04-17		.txt	text/plain	3501	243	53	In this paper, we propose a soft labels guided graph attention network (SLGAT) to improve the performance of node representation learning by leveraging generated pseudo labels. Graph attention networks (GAT) [23] , which is one of the most representative GCNs, learns the weights for neighborhood aggregation via self-attention mechanism [22] and achieves promising performance on semi-supervised node classification problem. In this paper, we propose soft labels guided attention networks (SLGAT) for semi-supervised node representation learning. First, SLGAT aggregates the features of neighbors using convolutional networks and predicts soft labels for each node based on the learned embeddings. The weights for neighborhood aggregation learned by a feedforward neural network based on both label information of central nodes and features of neighboring nodes, which can lead to learning more discriminative node representations for classification. Unlike the prior graph attention networks [23, 28] , we use label information as guidance to learn the weights of neighboring nodes for feature aggregation.	./cache/cord-024437-r5wnz7rq.txt	./txt/cord-024437-r5wnz7rq.txt