arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2101.00417cs.LG
收藏

基于随机游走图卷积网络的重构图表示学习

Representation Learning of Reconstructed Graphs Using Random Walk Graph Convolutional Network

Beihang University(北京航空航天大学);Peng Cheng Laboratory(鹏城实验室)

Xing Li, Wei Wei, Xiangnan Feng, Zhiming Zheng

摘要:

图因其简单的拓扑结构而经常用于组织数据,因此在机器学习中发挥着关键作用。事实证明,通过图表示学习获得的低维嵌入表示在各种典型任务中非常有用,例如节点分类,内容推荐和链接预测。然而,现有的方法大多从微观结构(即,图中的边),忽略介观结构(高阶局部结构)。在这里,我们提出了wGCN --一种新的框架,利用随机游走来获得图的节点特定的介观结构,并利用这些介观结构来重建图和组织节点的特征信息。我们的方法可以有效地为以前看不见的数据生成节点嵌入,这已经在引文网络和社交网络上进行的一系列实验中得到了证明(我们的方法比基线方法更有优势)。我们认为,结合高阶局部结构信息可以更高效地挖掘网络的潜力,这将大大提高图神经网络的学习效率,促进新的学习模型的建立。

英文摘要:

Graphs are often used to organize data because of their simple topological structure, and therefore play a key role in machine learning. And it turns out that the low-dimensional embedded representation obtained by graph representation learning are extremely useful in various typical tasks, such as node classification, content recommendation and link prediction. However, the existing methods mostly start from the microstructure (i.e., the edges) in the graph, ignoring the mesoscopic structure (high-order local structure). Here, we propose wGCN -- a novel framework that utilizes random walk to obtain the node-specific mesoscopic structures of the graph, and utilizes these mesoscopic structures to reconstruct the graph And organize the characteristic information of the nodes. Our method can effectively generate node embeddings for previously unseen data, which has been proven in a series of experiments conducted on citation networks and social networks (our method has advantages over baseline methods). We believe that combining high-order local structural information can more efficiently explore the potential of the network, which will greatly improve the learning efficiency of graph neural network and promote the establishment of new learning models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑