Variational Gridded Graph Convolution Network for Node Classification

作     者：Xiaobin Hong Tong Zhang Zhen Cui Jian Yang Xiaobin Hong;Tong Zhang;Zhen Cui;Jian Yang

作者机构：Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of EducationSchool of Computer Science and EngineeringNanjing University of Science and TechnologyNanjing 210094China 

出 版 物：《IEEE/CAA Journal of Automatica Sinica》 (自动化学报（英文版）)

年 卷 期：2021年第8卷第10期

页      面：1697-1708页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported by the Natural Science Foundation of Jiangsu Province(BK20190019,BK20190452) the National Natural Science Foundation of China(62072244,61906094) the Natural Science Foundation of Shandong Province(ZR2020LZH008) 

主　　题：Graph coarsening gridding node classification random walk variational convolution 

摘      要：The existing graph convolution methods usually suffer high computational burdens,large memory requirements,and intractable *** this paper,we propose a high-efficient variational gridded graph convolution network(VG-GCN)to encode non-regular graph data,which overcomes all these aforementioned *** capture graph topology structures efficiently,in the proposed framework,we propose a hierarchically-coarsened random walk(hcr-walk)by taking advantage of the classic random walk and node/edge *** hcr-walk greatly mitigates the problem of exponentially explosive sampling times which occur in the classic version,while preserving graph structures *** efficiently encode local hcr-walk around one reference node,we project hcrwalk into an ordered space to form image-like grid data,which favors those conventional convolution *** of the direct 2-D convolution filtering,a variational convolution block(VCB)is designed to model the distribution of the randomsampling hcr-walk inspired by the well-formulated variational *** experimentally validate the efficiency and effectiveness of our proposed VG-GCN,which has high computation speed,and the comparable or even better performance when compared with baseline GCNs.