Learning interaction rules from multi-animal trajectories via augmented behavioral models

Abstract

Extracting the interaction rules of biological agents from movement sequences pose challenges in various domains. Granger causality is a practical framework for analyzing the interactions from observed time-series data; however, this framework ignores the structures and assumptions of the generative process in animal behaviors, which may lead to interpretational problems and sometimes erroneous assessments of causality. In this paper, we propose a new framework for learning Granger causality from multi-animal trajectories via augmented theory-based behavioral models with interpretable data-driven models. We adopt an approach for augmenting incomplete multi-agent behavioral models described by time-varying dynamical systems with neural networks. For efficient and interpretable learning, our model leverages theory-based architectures separating navigation and motion processes, and the theory-guided regularization for reliable behavioral modeling. This can provide interpretable signs of Granger-causal effects over time, i.e., when specific others cause the approach or separation. In experiments using synthetic datasets, our method achieved better performance than various baselines. We then analyzed multi-animal datasets of mice, flies, birds, and bats, which verified our method and obtained novel biological insights.

24 pages, 5 figures, to appear in NeurIPS 2021

References in corpus (10)

• Hierarchical group dynamics in pigeon flocks
• Universal power law governing pedestrian interactions
• Local information transfer as a spatiotemporal filter for complex systems
• Kernel Granger causality and the analysis of dynamical networks
• Multiple Futures Prediction
• Generating Long-term Trajectories Using Deep Hierarchical Networks
• Social Attention for Autonomous Decision-Making in Dense Traffic
• SimGANs: Simulator-Based Generative Adversarial Networks for ECG Synthesis to Improve Deep ECG Classification
• Learning recurrent representations for hierarchical behavior modeling
• Discovering Nonlinear Relations with Minimum Predictive Information Regularization