Behaviour Modelling of Social Animals via Causal Structure Discovery and Graph Neural Networks

Gaël Gendron (NAOInstitute, The University of Auckland), Yang Chen (NAOInstitute, The University of Auckland), Mitchell Rogers (NAOInstitute, The University of Auckland), Yiping Liu (NAOInstitute, The University of Auckland), Mihailo Azhar (NAOInstitute, The University of Auckland), Shahrokh Heidari (NAOInstitute, The University of Auckland), David Arturo Soriano Valdez (NAOInstitute, The University of Auckland), Kobe Knowles (NAOInstitute, The University of Auckland), Padriac O'Leary (NAOInstitute, The University of Auckland), Simon Eyre (Wellington Zoo), Michael Witbrock (NAOInstitute, The University of Auckland), Gillian Dobbie (NAOInstitute, The University of Auckland), Jiamou Liu (NAOInstitute, The University of Auckland), Patrice Delmas (NAOInstitute, The University of Auckland)

Abstract

Better understanding the natural world is a crucial task with a wide range of applications. In environments with close proximity between humans and animals, such as zoos, it is essential to better understand the causes behind animal behaviour to predict unusual changes, mitigate their detrimental effects and increase the well-being of animals. However, the complex social behaviours of mammalian groups remain largely unexplored. In this work, we propose a method to build behavioural models using causal structure discovery and graph neural networks for time series. We apply this method to a mob of meerkats in a zoo environment and study its ability to predict future actions and model the behaviour distribution at an individual-level and at a group level. We show that our method can match and outperform standard deep learning architectures and generate more realistic data, while using fewer parameters and providing increased interpretability.