arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1912.09575cs.LGstat.ML
收藏

扩展图卷积网络的标号集

Expanding Label Sets for Graph Convolutional Networks

Abdullah Gül University(阿卜杜拉·居尔大学);Case Western Reserve University(凯斯西储大学)

Mustafa Coskun, Burcu Bakir Gungor, Mehmet Koyuturk

摘要:

近年来,图卷积网络(GCN)及其变体已被广泛用于涉及图的学习任务。这些任务包括推荐系统、节点分类等。在节点分类问题中,输入是一个图,其中边表示节点对之间的关联,多维特征向量与节点相关联,并且图中的一些节点具有已知的标签。我们的目标是预测未标记的节点的标签,使用节点的功能,结合图形拓扑。虽然GCN已成功应用于此问题,但它们继承自传统深度学习模型的警告对GCN在节点分类中的广泛应用构成了重大挑战。一个这样的警告是,训练GCN需要大量的标记训练实例,这在现实环境中通常不是这种情况。为了弥补这一要求,最先进的方法利用基于网络扩散的方法在训练GCN之前在网络中传播标签。然而,这些方法忽略了网络扩散方法的倾向,即偏向于接近中心,导致标签传播到图中连接良好的节点。为了解决这个问题,我们在这里提出了一种通过以下三个步骤推断GCN中节点标签的替代方法:(i)对网络进行聚类以识别社区,(ii)使用网络扩散算法来量化每个节点与社区的接近度,从而获得每个节点的低维拓扑简档,(iii)比较这些拓扑简档以识别与标记的节点最相似的节点。

英文摘要:

In recent years, Graph Convolutional Networks (GCNs) and their variants have been widely utilized in learning tasks that involve graphs. These tasks include recommendation systems, node classification, among many others. In node classification problem, the input is a graph in which the edges represent the association between pairs of nodes, multi-dimensional feature vectors are associated with the nodes, and some of the nodes in the graph have known labels. The objective is to predict the labels of the nodes that are not labeled, using the nodes features, in conjunction with graph topology. While GCNs have been successfully applied to this problem, the caveats that they inherit from traditional deep learning models pose significant challenges to broad utilization of GCNs in node classification. One such caveat is that training a GCN requires a large number of labeled training instances, which is often not the case in realistic settings. To remedy this requirement, state-of-the-art methods leverage network diffusion-based approaches to propagate labels across the network before training GCNs. However, these approaches ignore the tendency of the network diffusion methods in biasing proximity with centrality, resulting in the propagation of labels to the nodes that are well-connected in the graph. To address this problem, here we present an alternate approach to extrapolating node labels in GCNs in the following three steps: (i) clustering of the network to identify communities, (ii) use of network diffusion algorithms to quantify the proximity of each node to the communities, thereby obtaining a low-dimensional topological profile for each node, (iii) comparing these topological profiles to identify nodes that are most similar to the labeled nodes.

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。

↑