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

2022/08/12 by Liu, Yirui, Qiao, Xinghao, Wang, Liying +1
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2208.06322

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.

Related

• Graphs as Tools to Improve Deep Learning Methods
• Boosting Graph Neural Networks by Injecting Pooling in Message Passing
• Probability Passing for Graph Neural Networks: Graph Structure and Representations Joint Learning
• Probabilistically Rewired Message-Passing Neural Networks
• Towards Understanding Graph Neural Networks: An Algorithm Unrolling Perspective