HpLapGCN: Hypergraph p-Laplacian graph convolutional networks
HpLapGCN: Hypergraph p-Laplacian graph convolutional networks
复制标题
HpLapGCN：超图 p-拉普拉斯图卷积网络
DOI：
10.1016/j.neucom.2019.06.068
复制
发表时间：
2019-10-14
期刊：
影响因子：
6
通讯作者：
Nie, Liqiang
中科院分区：
文献类型：
--
作者：
Fu, Sichao;Liu, Weifeng;Nie, Liqiang
目前，图的表示学习已被证明是提取图结构化数据特征的重要技术。近年来，许多图表示学习（GRL）算法，如拉普拉斯特征映射（LE），Node 2 vec和图卷积网络（GCN），已被报道，并取得了巨大的成功，在节点分类任务。最具代表性的GCN融合了数据的特征信息和结构信息，旨在推广卷积神经网络（CNN）来学习具有任意结构的数据特征。然而，如何准确地表达数据的结构信息仍然是一个巨大的挑战。在本文中，我们利用超图p-Laplacian保持样本的局部几何，然后提出了一个有效的变种的GCN，即超图p-Laplacian图卷积网络（HpLapGCN）。由于超图p-Laplacian是图Laplacian的推广，HpLapGCN模型在学习更具代表性的数据特征方面表现出巨大的潜力。特别地，我们简化并推导出谱超图p-Laplacian卷积的一阶近似。因此，我们可以得到一个更有效的逐层聚集规则。在Citeseer和Cora数据集上的大量实验结果表明，与GCN和p-Laplacian GCN（pLapGCN）相比，本文提出的模型具有更好的性能。(C)2019 Elsevier B. V.版权所有。
Currently, the representation learning of a graph has been proved to be a significant technique to extract graph structured data features. In recent years, many graph representation learning (GRL) algorithms, such as Laplacian Eigenmaps (LE), Node2vec and graph convolutional networks (GCN), have been reported and have achieved great success on node classification tasks. The most representative GCN fuses the feature information and structure information of data, which aims to generalize convolutional neural networks (CNN) to learn data features with arbitrary structure. However, how to exactly express the structure information of data is still an enormous challenge. In this paper, we utilize hypergraph p-Laplacian to preserve the local geometry of samples and then propose an effective variant of GCN, i.e. hypergraph p-Laplacian graph convolutional networks (HpLapGCN). Since hypergraph p-Laplacian is a generalization of the graph Laplacian, HpLapGCN model shows great potential to learn more representative data features. In particular, we simplify and deduce a one-order approximation of spectral hypergraph p-Laplacian convolutions. Thus, we can get a more efficient layer-wise aggregate rule. Extensive experiment results on the Citeseer and Cora datasets prove that our proposed model achieves better performance compare with GCN and p-Laplacian GCN (pLapGCN). (C) 2019 Elsevier B.V. All rights reserved.