SGCN: A Graph Sparsifier Based on Graph Convolutional Networks

SGCN: A Graph Sparsifier Based on Graph Convolutional Networks
复制标题

DOI:
10.1007/978-3-030-47426-3_22
复制
发表时间:
2020-04-17
期刊:
Advances in Knowledge Discovery and Data Mining
影响因子:
--
通讯作者:
Zafarani R
Zafarani R
中科院分区:
其他
文献类型:
--
作者:
Li J;Zhang T;Tian H;Jin S;Fardad M;Zafarani R

文献摘要

参考文献

被引文献

相似文献

图形在全球范围内以及科学和工程中无处不在。随着尺寸的图表的增长,大图上的节点分类也可以是空间和耗时的,即使使用强大的分类器,例如图形卷积网络(GCN)。因此,尤其是提出一些问题,特别是在保持节点分类的预测性能的同时,还是在特定子图上进行培训分类器,而不是整个图表,而不是在节点分类中的性能损失有限的情况下。为了解决这些问题,我们提出了稀疏的图形卷积网络(SGCN),这是一种神经网络图弹药符,通过修剪一些边缘通过修剪一些边缘来放松图。我们将稀疏作为一个优化问题,我们通过基于乘数的交替方向方法(ADMM)解决方案来解决。我们表明,由SGCN提供的稀疏图可以用作GCN的输入,从而与GCN,DeepSwalk和Graphsage中的原始图相同,从而获得更好或可比较的节点分类性能。
Graphs are ubiquitous across the globe and within science and engineering. With graphs growing in size, node classification on large graphs can be space and time consuming, even with powerful classifiers such as Graph Convolutional Networks (GCNs). Hence, some questions are raised, particularly, whether one can keep only some of the edges of a graph while maintaining prediction performance for node classification, or train classifiers on specific subgraphs instead of a whole graph with limited performance loss in node classification. To address these questions, we propose Sparsified Graph Convolutional Network (SGCN), a neural network graph sparsifier that sparsifies a graph by pruning some edges. We formulate sparsification as an optimization problem, which we solve by an Alternating Direction Method of Multipliers (ADMM)-based solution. We show that sparsified graphs provided by SGCN can be used as inputs to GCN, leading to better or comparable node classification performance with that of original graphs in GCN, DeepWalk, and GraphSAGE.
DOI: 10.1137/140990309
发表时间: 2016-01-01
影响因子: 3.1
作者:
Hong, Mingyi;Luo, Zhi-Quan;Razaviyayn, Meisam
通讯作者: Razaviyayn, Meisam
DOI: 10.1109/tnn.2008.2005605
发表时间: 2009-01-01
影响因子: --
作者:
Scarselli, Franco;Gori, Marco;Monfardini, Gabriele
通讯作者: Monfardini, Gabriele
DOI: 10.1109/tnnls.2020.2978386
发表时间: 2021-01-01
影响因子: 10.4
作者:
Wu, Zonghan;Pan, Shirui;Yu, Philip S.
通讯作者: Yu, Philip S.
DOI: 10.1080/00207179.2017.1316016
发表时间: 2020-01-01
影响因子: 2.1
作者:
Takapoui, Reza;Moehle, Nicholas;Bemporad, Alberto
通讯作者: Bemporad, Alberto
DOI: 10.1073/pnas.0808904106
发表时间: 2009-04-21
影响因子: 11.1
作者:
Serrano, M. Angeles;Boguna, Marian;Vespignani, Alessandro
通讯作者: Vespignani, Alessandro