EEGNN: edge enhanced graph neural network with a Bayesian nonparametric graph model

Liu, Yirui, Qiao, Xinghao ORCID: 0000-0002-6546-6595, Wang, Liying and Lam, Jessica (2023) EEGNN: edge enhanced graph neural network with a Bayesian nonparametric graph model. Proceedings of Machine Learning Research, 206. pp. 2132-2146. ISSN 1938-7228

Text (EEGNN. Edge Enhanced Graph Neural Network with a Bayesian) - Accepted Version Download (887kB)

• Scopus publication
• Author

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.

Item Type:	Article
Official URL:	https://proceedings.mlr.press/v206/
Additional Information:	© 2023 The Author(s)
Divisions:	Statistics
Subjects:	H Social Sciences > HA Statistics Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Date Deposited:	04 Aug 2023 15:39
Last Modified:	25 Apr 2024 07:43
URI:	http://eprints.lse.ac.uk/id/eprint/119918

Actions (login required)

View Item