EEGNN: Edge Enhanced Graph Neural Network with a Bayesian Nonparametric Graph Model
This work addresses a key challenge in training deep GNNs for graph-based tasks, offering a novel explanation and improvement method, though it appears incremental as it builds on existing message-passing GNNs.
The paper tackles the performance deterioration in deep graph neural networks (GNNs) by proposing a new explanation called 'mis-simplification' and introduces EEGNN, a framework that uses a Bayesian nonparametric graph model to enhance edges, resulting in a considerable performance increase over baselines on various datasets.
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.