NGAT:attention in breadth and depth exploration for semi-supervised graph representation learning  

作　　者：Jianke HU Yin ZHANG 

机构地区：[1]College of Computer Science and Technology,Zhejiang University,Hangzhou 310027,China

出　　处：《Frontiers of Information Technology & Electronic Engineering》2022年第3期409-421,共13页信息与电子工程前沿（英文版）

基　　金：Project supptjrted by China Knowledge Centre for Engineering Sciences and Technology(CKCEST)。

摘　　要：Recently,graph neural networks(GNNs)have achieved remarkable performance in representation learning on graph-structured data.However,as the number of network layers increases,GNNs based on the neighborhood aggregation strategy deteriorate due to the problem of oversmoothing,which is the major bottleneck for applying GNNs to real-world graphs.Many efforts have been made to improve the process of feature information aggregation from directly connected nodes,i.e.,breadth exploration.However,these models perform the best only in the case of three or fewer layers,and the performance drops rapidly for deep layers.To alleviate oversmoothing,we propose a nested graph attention network(NGAT),which can work in a semi-supervised manner.In addition to breadth exploration,a k-layer NGAT uses a layer-wise aggregation strategy guided by the attention mechanism to selectively leverage feature information from the k;-order neighborhood,i.e.,depth exploration.Even with a 10-layer or deeper architecture,NGAT can balance the need for preserving the locality(including root node features and the local structure)and aggregating the information from a large neighborhood.In a number of experiments on standard node classification tasks,NGAT outperforms other novel models and achieves state-of-the-art performance.

关 键 词：Graph learning Semi-supervised learning Node classification ATTENTION 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]