LFGCN: Levitating over Graphs with Levy Flights
LFGCN: Levitating over Graphs with Levy Flights
复制标题
DOI：
10.1109/icdm50108.2020.00109
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Yuzhou Chen;Y. Gel;Konstantin Avrachenkov
中科院分区：
文献类型：
--
作者：
Yuzhou Chen;Y. Gel;Konstantin Avrachenkov
我们提出了一种新的用于半监督学习的l<s:1>飞行图卷积网络（LFGCN）方法，该方法将l<s:1>飞行图转换为图上的随机行走，从而既可以准确地解释图的内在拓扑结构，又可以大大提高分类性能，特别是对于异构图。在此基础上，我们提出了一种新的基于Girvan-Newman论证的优先P-DropEdge方法。也就是说，与DropEdge中的均匀去除边缘不同，我们遵循Girvan-Newman算法，利用边缘间性信息检测网络外围结构，然后根据边缘间性中心性去除边缘。我们在半监督节点分类任务上的实验结果表明，LFGCN与P-DropEdge的结合加速了训练任务，增加了稳定性，进一步提高了学习到的图拓扑结构的预测精度。最后，在我们的案例研究中，我们将LFGCN的机制和其他深度网络工具引入电网网络分析- GDL的效用尚未开发的领域。
We propose a new Lévy Flights Graph Convolutional Networks (LFGCN) method for semi-supervised learning, which casts the Lévy Flights into random walks on graphs and, as a result, allows both to accurately account for the intrinsic graph topology and to substantially improve classification performance, especially for heterogeneous graphs. Furthermore, we propose a new preferential P-DropEdge method based on the Girvan-Newman argument. That is, in contrast to uniform removing of edges as in DropEdge, following the Girvan-Newman algorithm, we detect network periphery structures using information on edge betweenness and then remove edges according to their betweenness centrality. Our experimental results on semi-supervised node classification tasks demonstrate that the LFGCN coupled with P-DropEdge accelerates the training task, increases stability and further improves predictive accuracy of learned graph topology structure. Finally, in our case studies we bring the machinery of LFGCN and other deep networks tools to analysis of power grid networks – the area where the utility of GDL remains untapped.