Structure-Aware Consensus Network on Graphs with Few Labeled Nodes

TL;DR

This paper introduces SACN, a novel graph neural network that effectively leverages structural information and unlabeled data through a consensus learning strategy, significantly improving node classification with few labels.

Contribution

SACN presents a structure-aware consensus learning approach within a single-branch multiview framework, enhancing performance in low-label scenarios.

Findings

Outperforms state-of-the-art methods on benchmark datasets

Effective at very low label rates

Maintains computational simplicity

Abstract

Graph node classification with few labeled nodes presents significant challenges due to limited supervision. Conventional methods often exploit the graph in a transductive learning manner. They fail to effectively utilize the abundant unlabeled data and the structural information inherent in graphs. To address these issues, we introduce a Structure-Aware Consensus Network (SACN) from three perspectives. Firstly, SACN leverages a novel structure-aware consensus learning strategy between two strongly augmented views. The proposed strategy can fully exploit the potentially useful information of the unlabeled nodes and the structural information of the entire graph. Secondly, SACN uniquely integrates the graph's structural information to achieve strong-to-strong consensus learning, improving the utilization of unlabeled data while maintaining multiview learning. Thirdly, unlike two-branch graph neural network-based methods, SACN is designed for multiview feature learning within a single-branch architecture. Furthermore, a class-aware pseudolabel selection strategy helps address class imbalance and achieve effective weak-to-strong supervision. Extensive experiments on three benchmark datasets demonstrate SACN's superior performance in node classification tasks, particularly at very low label rates, outperforming state-of-the-art methods while maintaining computational simplicity.The source code is available at https://github.com/kunzhan/SACN