Graph convolutional networks: analysis, improvements and results
Graph convolutional networks: analysis, improvements and results
复制标题
DOI：
10.1007/s10489-021-02973-4
复制
发表时间：
2021-11-16
影响因子：
5.3
通讯作者：
Madden, Michael G.
中科院分区：
文献类型：
--
作者：
Ullah, Ihsan;Manzo, Mario;Madden, Michael G.
图可以表示复杂的数据组织，其中多个实体或活动之间存在依赖关系。这种复杂的结构给机器学习算法带来了挑战，特别是当与当前应用中的高维数据相结合时。图卷积网络被引入以采用来自深卷积网络(即卷积运算/层)的概念，这些概念已经显示出良好的效果。在此背景下，我们对现有的两个图卷积网络框架提出了两个主要的改进：(1)通过聚类系数来丰富拓扑信息；(2)通过增加致密层来重新设计网络结构。此外，我们提出了利用激活函数的凸组合和超参数优化的微小改进。我们在四个最先进的基准数据集上展示了广泛的结果。我们表明，我们的方法在三个数据集上获得了具有竞争力的结果，在第四个数据集上获得了最先进的结果，同时与竞争方法相比具有更低的计算成本。
A graph can represent a complex organization of data in which dependencies exist between multiple entities or activities. Such complex structures create challenges for machine learning algorithms, particularly when combined with the high dimensionality of data in current applications. Graph convolutional networks were introduced to adopt concepts from deep convolutional networks (i.e. the convolutional operations/layers) that have shown good results. In this context, we propose two major enhancements to two of the existing graph convolutional network frameworks: (1) topological information enrichment through clustering coefficients; and (2) structural redesign of the network through the addition of dense layers. Furthermore, we propose minor enhancements using convex combinations of activation functions and hyper-parameter optimization. We present extensive results on four state-of-art benchmark datasets. We show that our approach achieves competitive results for three of the datasets and state-of-the-art results for the fourth dataset while having lower computational costs compared to competing methods.