Semi-supervised learning with mixed-order graph convolutional networks

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. (c) 2021 Published by Elsevier Inc.

Automated summary

The proposed mixed-order graph convolutional networks (MOGCN) address the oversmoothing issue and underutilization of pseudo-labels of unlabeled nodes in semi-supervised learning. MOGCN consists of two modules: constructing multiple GCN learners with multi-order adjacency matrices and employing a novel ensemble module to efficiently combine results from these learners. Experimental results on three public benchmark datasets demonstrate that MOGCN consistently outperforms state-of-the-art methods.