Graph Partner Neural Networks for Semi-Supervised Learning on Graphs

TL;DR

This paper introduces Graph Partner Neural Networks (GPNN), a novel approach combining de-parameterized GCNs and MLPs, to effectively address over-smoothing in deep GCNs and achieve state-of-the-art results in node classification.

Contribution

The paper proposes GPNN, a new neural network architecture that mitigates over-smoothing in deep GCNs using a parameter-sharing MLP and novel loss functions, with theoretical and empirical validation.

Findings

GPNN outperforms existing methods on node classification tasks.

The proposed losses and graph enhancement improve model robustness.

Deep GPNN models achieve better results than shallow counterparts.

Abstract

Graph Convolutional Networks (GCNs) are powerful for processing graph-structured data and have achieved state-of-the-art performance in several tasks such as node classification, link prediction, and graph classification. However, it is inevitable for deep GCNs to suffer from an over-smoothing issue that the representations of nodes will tend to be indistinguishable after repeated graph convolution operations. To address this problem, we propose the Graph Partner Neural Network (GPNN) which incorporates a de-parameterized GCN and a parameter-sharing MLP. We provide empirical and theoretical evidence to demonstrate the effectiveness of the proposed MLP partner on tackling over-smoothing while benefiting from appropriate smoothness. To further tackle over-smoothing and regulate the learning process, we introduce a well-designed consistency contrastive loss and KL divergence loss. Besides, we present a graph enhancement technique to improve the overall quality of edges in graphs. While most GCNs can work with shallow architecture only, GPNN can obtain better results through increasing model depth. Experiments on various node classification tasks have demonstrated the state-of-the-art performance of GPNN. Meanwhile, extensive ablation studies are conducted to investigate the contributions of each component in tackling over-smoothing and improving performance.