当前位置: X-MOL 学术Inform. Sci. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Semi-supervised learning with mixed-order graph convolutional networks
Information Sciences Pub Date : 2021-05-28 , DOI: 10.1016/j.ins.2021.05.057
Jie Wang , Jianqing Liang , Junbiao Cui , Jiye Liang

Recently, graph convolutional networks (GCN) have made substantial progress in semi-supervised learning (SSL). However, established GCN-based methods have two major limitations. First, GCN-based methods are restricted by the oversmoothing issue that limits their ability to extract knowledge from distant but informative nodes. Second, most available GCN-based methods exploit only the feature information of unlabeled nodes, and the pseudo-labels of unlabeled nodes, which contain important information about the data distribution, are not fully utilized. To address these issues, we propose a novel end-to-end ensemble framework, which is named mixed-order graph convolutional networks (MOGCN). MOGCN consists of two modules. (1) It constructs multiple simple GCN learners with multi-order adjacency matrices, which can directly capture the high-order connectivity among the nodes to alleviate the problem of oversmoothing. (2) To efficiently combine the results from multiple GCN learners, MOGCN employs a novel ensemble module, in which the pseudo-labels of unlabeled nodes from various GCN learners are used to augment the diversity among the learners. We conduct experiments on three public benchmark datasets to evaluate the performance of MOGCN on semi-supervised node classification tasks. The experimental results demonstrate that MOGCN consistently outperforms state-of-the-art methods.



中文翻译:

混合阶图卷​​积网络的半监督学习

最近,图卷积网络(GCN)在半监督学习(SSL)方面取得了实质性进展。然而,已建立的基于 GCN 的方法有两个主要限制。首先,基于 GCN 的方法受到过度平滑问题的限制,这限制了它们从遥远但信息丰富的节点提取知识的能力。其次,大多数可用的基于 GCN 的方法仅利用未标记节点的特征信息,而未充分利用包含有关数据分布的重要信息的未标记节点的伪标签。为了解决这些问题,我们提出了一种新颖的端到端集成框架,称为混合阶图卷​​积网络(MOGCN)。MOGCN 由两个模块组成。(1) 用多阶邻接矩阵构造多个简单的GCN学习器,可以直接捕获节点之间的高阶连通性,以缓解过度平滑的问题。(2) 为了有效地组合来自多个 GCN 学习器的结果,MOGCN 采用了一种新颖的集成模块,其中来自各种 GCN 学习器的未标记节点的伪标签用于增加学习器之间的多样性。我们在三个公共基准数据集上进行实验,以评估 MOGCN 在半监督节点分类任务上的性能。实验结果表明 MOGCN 始终优于最先进的方法。其中来自各种 GCN 学习器的未标记节点的伪标签用于增加学习器之间的多样性。我们在三个公共基准数据集上进行实验,以评估 MOGCN 在半监督节点分类任务上的性能。实验结果表明 MOGCN 始终优于最先进的方法。其中来自各种 GCN 学习器的未标记节点的伪标签用于增加学习器之间的多样性。我们在三个公共基准数据集上进行实验,以评估 MOGCN 在半监督节点分类任务上的性能。实验结果表明 MOGCN 始终优于最先进的方法。

更新日期:2021-06-10
down
wechat
bug