A Safe Semi-supervised Graph Convolution Network

TL;DR

This paper introduces Safe-GCN, a semi-supervised graph convolutional network that iteratively labels high-confidence unlabeled data to improve learning performance while ensuring safe utilization of unlabeled data.

Contribution

The paper proposes a novel Safe-GCN framework with an iterative process for safe pseudo-labeling of unlabeled data in semi-supervised learning.

Findings

Safe-GCN outperforms several existing graph-based semi-supervised methods.

The iterative pseudo-labeling improves learning accuracy on citation datasets.

Safe-GCN effectively leverages unlabeled data without degrading performance.

Abstract

In the semi-supervised learning field, Graph Convolution Network (GCN), as a variant model of GNN, has achieved promising results for non-Euclidean data by introducing convolution into GNN. However, GCN and its variant models fail to safely use the information of risk unlabeled data, which will degrade the performance of semi-supervised learning. Therefore, we propose a Safe GCN framework (Safe-GCN) to improve the learning performance. In the Safe-GCN, we design an iterative process to label the unlabeled data. In each iteration, a GCN and its supervised version(S-GCN) are learned to find the unlabeled data with high confidence. The high-confidence unlabeled data and their pseudo labels are then added to the label set. Finally, both added unlabeled data and labeled ones are used to train a S-GCN which can achieve the safe exploration of the risk unlabeled data and enable safe use of large numbers of unlabeled data. The performance of Safe-GCN is evaluated on three well-known citation network datasets and the obtained results demonstrate the effectiveness of the proposed framework over several graph-based semi-supervised learning methods.