WMGCN: Weighted Meta-Graph Based Graph Convolutional Networks for Representation Learning in Heterogeneous Networks
WMGCN: Weighted Meta-Graph Based Graph Convolutional Networks for Representation Learning in Heterogeneous Networks
复制标题
DOI：
10.1109/access.2020.2977332
复制
发表时间：
2020-03
期刊：
影响因子：
3.9
通讯作者：
Jinli Zhang;Zongli Jiang;Zheng Chen;Xiaohua Hu
中科院分区：
文献类型：
--
作者：
Jinli Zhang;Zongli Jiang;Zheng Chen;Xiaohua Hu
网络嵌入通过将节点表示在低维空间中，已经成为分析异构网络的有效工具。虽然最近已经提出了许多方法来表示学习的HN，仍然有很大的改进空间。基于随机游走的方法是目前流行的网络嵌入学习方法，但它们具有随机性，且受样本游走长度的限制，难以捕捉网络结构信息。最近的一些研究提出了使用Meta路径来表示HNs中的样本关系。另一种流行的图学习模型，图卷积网络（GCN）被认为能够更好地利用网络拓扑结构，但目前GCN的设计是针对同构网络的。本文提出了一种新的结合元图和图卷积，基于元图的图卷积网络（MGCN）。为了完全捕获复杂的长语义信息，MGCN在HN中使用不同的元图。由于不同的元图表达不同的语义关系，MGCN学习不同元图的权重，以弥补应用GCN时语义的损失。此外，我们通过添加节点自重要性来改进当前卷积设计。为了验证我们的模型在学习特征表示方面的有效性，我们在四个真实世界的数据集和两个表示任务上进行了全面的实验：分类和链接预测。与其他流行的表示学习模型相比，WMGCN的表示可以将准确性分数提高约10%。更重要的是，WMGCN的功能学习优于其他流行的基线。实验结果清楚地表明，我们的模型是上级优于其他国家的最先进的表示学习算法。
Network embedding has been an effective tool to analyze heterogeneous networks (HNs) by representing nodes in a low-dimensional space. Although many recent methods have been proposed for representation learning of HNs, there is still much room for improvement. Random walks based methods are currently popular methods to learn network embedding; however, they are random and limited by the length of sampled walks, and have difficulty capturing network structural information. Some recent researches proposed using meta paths to express the sample relationship in HNs. Another popular graph learning model, the graph convolutional network (GCN) is known to be capable of better exploitation of network topology, but the current design of GCN is intended for homogenous networks. This paper proposes a novel combination of meta-graph and graph convolution, the meta-graph based graph convolutional networks (MGCN). To fully capture the complex long semantic information, MGCN utilizes different meta-graphs in HNs. As different meta-graphs express different semantic relationships, MGCN learns the weights of different meta-graphs to make up for the loss of semantics when applying GCN. In addition, we improve the current convolution design by adding node self-significance. To validate our model in learning feature representation, we present comprehensive experiments on four real-world datasets and two representation tasks: classification and link prediction. WMGCN’s representations can improve accuracy scores by up to around 10% in comparison to other popular representation learning models. What’s more, WMGCN’feature learning outperforms other popular baselines. The experimental results clearly show our model is superior over other state-of-the-art representation learning algorithms.