IDEAS home Printed from https://ideas.repec.org/p/ehl/lserod/119918.html
   My bibliography  Save this paper

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

Author

Listed:
  • Liu, Yirui
  • Qiao, Xinghao
  • Wang, Liying
  • Lam, Jessica

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.

Suggested Citation

  • Liu, Yirui & Qiao, Xinghao & Wang, Liying & Lam, Jessica, 2023. "EEGNN: edge enhanced graph neural network with a Bayesian nonparametric graph model," LSE Research Online Documents on Economics 119918, London School of Economics and Political Science, LSE Library.
  • Handle: RePEc:ehl:lserod:119918
    as

    Download full text from publisher

    File URL: http://eprints.lse.ac.uk/119918/
    File Function: Open access version.
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. François Caron & Emily B. Fox, 2017. "Sparse graphs using exchangeable random measures," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 79(5), pages 1295-1366, November.
    2. Ghosal,Subhashis & van der Vaart,Aad, 2017. "Fundamentals of Nonparametric Bayesian Inference," Cambridge Books, Cambridge University Press, number 9780521878265.
    3. Adrien Todeschini & Xenia Miscouridou & François Caron, 2020. "Exchangeable random measures for sparse and modular graphs with overlapping communities," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 82(2), pages 487-520, April.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Bikramjit Das & Tiandong Wang & Gengling Dai, 2022. "Asymptotic Behavior of Common Connections in Sparse Random Networks," Methodology and Computing in Applied Probability, Springer, vol. 24(3), pages 2071-2092, September.
    2. Caron, François & Panero, Francesca & Rousseau, Judith, 2023. "On sparsity, power-law, and clustering properties of graphex processes," LSE Research Online Documents on Economics 119794, London School of Economics and Political Science, LSE Library.
    3. Qiao, Xinghao & Liu, Yirui & Lam, Jessica, 2022. "CATVI: conditional and adaptively truncated variational inference for hierarchical Bayesian nonparametric models," LSE Research Online Documents on Economics 114639, London School of Economics and Political Science, LSE Library.
    4. Qianwen Tan & Subhashis Ghosal, 2021. "Bayesian Analysis of Mixed-effect Regression Models Driven by Ordinary Differential Equations," Sankhya B: The Indian Journal of Statistics, Springer;Indian Statistical Institute, vol. 83(1), pages 3-29, May.
    5. Laura Liu & Hyungsik Roger Moon & Frank Schorfheide, 2023. "Forecasting with a panel Tobit model," Quantitative Economics, Econometric Society, vol. 14(1), pages 117-159, January.
    6. Gael M. Martin & David T. Frazier & Christian P. Robert, 2020. "Computing Bayes: Bayesian Computation from 1763 to the 21st Century," Monash Econometrics and Business Statistics Working Papers 14/20, Monash University, Department of Econometrics and Business Statistics.
    7. A Stefano Caria & Grant Gordon & Maximilian Kasy & Simon Quinn & Soha Osman Shami & Alexander Teytelboym, 2024. "An Adaptive Targeted Field Experiment: Job Search Assistance for Refugees in Jordan," Journal of the European Economic Association, European Economic Association, vol. 22(2), pages 781-836.
    8. Reiß, Markus & Schmidt-Hieber, Johannes, 2020. "Posterior contraction rates for support boundary recovery," Stochastic Processes and their Applications, Elsevier, vol. 130(11), pages 6638-6656.
    9. Dmitry B. Rokhlin, 2021. "Relative utility bounds for empirically optimal portfolios," Mathematical Methods of Operations Research, Springer;Gesellschaft für Operations Research (GOR);Nederlands Genootschap voor Besliskunde (NGB), vol. 93(3), pages 437-462, June.
    10. Angelos Dassios & Junyi Zhang, 2023. "Exact Simulation of Poisson-Dirichlet Distribution and Generalised Gamma Process," Methodology and Computing in Applied Probability, Springer, vol. 25(2), pages 1-21, June.
    11. Suzanne Sniekers & Aad Vaart, 2020. "Adaptive Bayesian credible bands in regression with a Gaussian process prior," Sankhya A: The Indian Journal of Statistics, Springer;Indian Statistical Institute, vol. 82(2), pages 386-425, August.
    12. Shota Gugushvili & Frank van der Meulen & Moritz Schauer & Peter Spreij, 2018. "Nonparametric Bayesian volatility estimation," Papers 1801.09956, arXiv.org, revised Mar 2019.
    13. Riva Palacio, Alan & Leisen, Fabrizio, 2018. "Integrability conditions for compound random measures," Statistics & Probability Letters, Elsevier, vol. 135(C), pages 32-37.
    14. Martin Burda & Remi Daviet, 2023. "Hamiltonian sequential Monte Carlo with application to consumer choice behavior," Econometric Reviews, Taylor & Francis Journals, vol. 42(1), pages 54-77, January.
    15. Billio, Monica & Casarin, Roberto & Rossini, Luca, 2019. "Bayesian nonparametric sparse VAR models," Journal of Econometrics, Elsevier, vol. 212(1), pages 97-115.
    16. Agustín G. Nogales, 2022. "On Consistency of the Bayes Estimator of the Density," Mathematics, MDPI, vol. 10(4), pages 1-6, February.
    17. Minerva Mukhopadhyay & Didong Li & David B. Dunson, 2020. "Estimating densities with non‐linear support by using Fisher–Gaussian kernels," Journal of the Royal Statistical Society Series B, Royal Statistical Society, vol. 82(5), pages 1249-1271, December.
    18. Meier, Alexander & Kirch, Claudia & Meyer, Renate, 2020. "Bayesian nonparametric analysis of multivariate time series: A matrix Gamma Process approach," Journal of Multivariate Analysis, Elsevier, vol. 175(C).
    19. Griffin, Jim, 2019. "Two part envelopes for rejection sampling of some completely random measures," Statistics & Probability Letters, Elsevier, vol. 151(C), pages 36-41.
    20. I. Votsi & G. Gayraud & V. S. Barbu & N. Limnios, 2021. "Hypotheses testing and posterior concentration rates for semi-Markov processes," Statistical Inference for Stochastic Processes, Springer, vol. 24(3), pages 707-732, October.

    More about this item

    JEL classification:

    • C1 - Mathematical and Quantitative Methods - - Econometric and Statistical Methods and Methodology: General

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:ehl:lserod:119918. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: LSERO Manager (email available below). General contact details of provider: https://edirc.repec.org/data/lsepsuk.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.