A Graph Data Augmentation Strategy with Entropy Preservation

TL;DR

This paper introduces a novel graph data augmentation method that preserves entropy and structural information, improving GCN semi-supervised learning and robustness against over-smoothing.

Contribution

It proposes a new entropy-based measure and a data augmentation strategy that maintains graph structure and entropy, enhancing GCN performance.

Findings

Improves semi-supervised node classification accuracy.

Enhances robustness of GCN training.

Maintains graph entropy during augmentation.

Abstract

The Graph Convolutional Networks (GCN) proposed by Kipf and Welling is an effective model for semi-supervised learning, but faces the obstacle of over-smoothing, which will weaken the representation ability of GCN. Recently some works are proposed to tackle above limitation by randomly perturbing graph topology or feature matrix to generate data augmentations as input for training. However, these operations inevitably do damage to the integrity of information structures and have to sacrifice the smoothness of feature manifold. In this paper, we first introduce a novel graph entropy definition as a measure to quantitatively evaluate the smoothness of a data manifold and then point out that this graph entropy is controlled by triangle motif-based information structures. Considering the preservation of graph entropy, we propose an effective strategy to generate randomly perturbed training data but maintain both graph topology and graph entropy. Extensive experiments have been conducted on real-world datasets and the results verify the effectiveness of our proposed method in improving semi-supervised node classification accuracy compared with a surge of baselines. Beyond that, our proposed approach could significantly enhance the robustness of training process for GCN.