Inferring the interaction rules of complex systems with graph neural networks and approximate Bayesian computation

Gaskell, J. , Campioni, N., Morales, J. M. , Husmeier, D. and Torney, C. J. (2023) Inferring the interaction rules of complex systems with graph neural networks and approximate Bayesian computation. Journal of the Royal Society: Interface, 20(198), 20220676. (doi: 10.1098/rsif.2022.0676) (PMID:36596456)

[img] Text
286295.pdf - Accepted Version
Available under License Creative Commons Attribution.

2MB

Abstract

Inferring the underlying processes that drive collective behaviour in biological and social systems is a significant statistical and computational challenge. While simulation models have been successful in qualitatively capturing many of the phenomena observed in these systems in a variety of domains, formally fitting these models to data remains intractable. Recently, approximate Bayesian computation (ABC) has been shown to be an effective approach to inference if the likelihood function for a model is unavailable. However, a key difficulty in successfully implementing ABC lies with the design, selection and weighting of appropriate summary statistics, a challenge that is especially acute when modelling high dimensional complex systems. In this work, we combine a Gaussian process accelerated ABC method with the automatic learning of summary statistics via graph neural networks. Our approach bypasses the need to design a model-specific set of summary statistics for inference. Instead, we encode relational inductive biases into a neural network using a graph embedding and then extract summary statistics automatically from simulation data. To evaluate our framework, we use a model of collective animal movement as a test bed and compare our method to a standard summary statistics approach and a linear regression-based algorithm.

Item Type:Articles
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Gaskell, Dr Jennifer and Morales, Professor Juan and Husmeier, Professor Dirk and Campioni, Nazareno and Torney, Professor Colin
Creator Roles:
Gaskell, J.Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Project administration, Software, Validation, Visualization, Writing – original draft, Writing – review and editing
Campioni, N.Conceptualization, Visualization
Morales, J. M.Conceptualization, Funding acquisition, Investigation, Supervision, Writing – review and editing
Husmeier, D.Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Supervision, Visualization, Writing – review and editing
Torney, C. J.Conceptualization, Data curation, Formal analysis, Funding acquisition, Investigation, Methodology, Project administration, Resources, Software, Supervision, Validation, Visualization, Writing – review and editing
Authors: Gaskell, J., Campioni, N., Morales, J. M., Husmeier, D., and Torney, C. J.
College/School:College of Medical Veterinary and Life Sciences > School of Biodiversity, One Health & Veterinary Medicine
College of Science and Engineering > School of Mathematics and Statistics > Mathematics
College of Science and Engineering > School of Mathematics and Statistics > Statistics
Journal Name:Journal of the Royal Society: Interface
Publisher:The Royal Society
ISSN:1742-5689
ISSN (Online):1742-5662
Published Online:04 January 2023
Copyright Holders:Copyright © 2023 The Authors
First Published:First published in Journal of the Royal Society: Interface 20(198): 20220676
Publisher Policy:Reproduced in accordance with the publisher copyright policy
Related URLs:

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
303337Multiscale methods for inferring the structure and dynamics of collective animal behaviourColin TorneyLeverhulme Trust (LEVERHUL)RPG-2018-398M&S - Mathematics
305798Juan Morales Visiting ProfessorshipColin TorneyLeverhulme Trust (LEVERHUL)VP2-2018-063M&S - Mathematics
308255The SofTMech Statistical Emulation and Translation HubDirk HusmeierEngineering and Physical Sciences Research Council (EPSRC)EP/T017899/1M&S - Statistics