EEGNN: Edge Enhanced Graph Neural Network with a Bayesian Nonparametric Graph Model

TL;DR

This paper introduces EEGNN, a novel graph neural network framework that leverages a Bayesian nonparametric graph model to enhance deep GNN performance by addressing structural mis-simplification issues.

Contribution

The paper proposes EEGNN, integrating a Dirichlet mixture Poisson graph model with GNNs to better capture graph structure and improve deep GNN performance.

Findings

EEGNN outperforms baseline GNNs on multiple datasets.

Using DMPGM improves structural information capture.

Significant performance gains in deep GNNs.

Abstract

Training deep graph neural networks (GNNs) poses a challenging task, as the performance of GNNs may suffer from the number of hidden message-passing layers. The literature has focused on the proposals of {over-smoothing} and {under-reaching} to explain the performance deterioration of deep GNNs. In this paper, we propose a new explanation for such deteriorated performance phenomenon, {mis-simplification}, that is, mistakenly simplifying graphs by preventing self-loops and forcing edges to be unweighted. We show that such simplifying can reduce the potential of message-passing layers to capture the structural information of graphs. In view of this, we propose a new framework, edge enhanced graph neural network (EEGNN). EEGNN uses the structural information extracted from the proposed Dirichlet mixture Poisson graph model (DMPGM), a Bayesian nonparametric model for graphs, to improve the performance of various deep message-passing GNNs. We propose a Markov chain Monte Carlo inference framework for DMPGM. Experiments over different datasets show that our method achieves considerable performance increase compared to baselines.