Capturing Actionable Dynamics with Structured Latent Ordinary Differential Equations

Abstract

End-to-end learning of dynamical systems with black-box models, such as neural ordinary differential equations (ODEs), provides a flexible framework for learning dynamics from data without prescribing a mathematical model for the dynamics. Unfortunately, this flexibility comes at the cost of understanding the dynamical system, for which ODEs are used ubiquitously. Further, experimental data are collected under various conditions (inputs), such as treatments, or grouped in some way, such as part of sub-populations. Understanding the effects of these system inputs on system outputs is crucial to have any meaningful model of a dynamical system. To that end, we propose a structured latent ODE model that explicitly captures system input variations within its latent representation. Building on a static latent variable specification, our model learns (independent) stochastic factors of variation for each input to the system, thus separating the effects of the system inputs in the latent space. This approach provides actionable modeling through the controlled generation of time-series data for novel input combinations (or perturbations). Additionally, we propose a flexible approach for quantifying uncertainties, leveraging a quantile regression formulation. Results on challenging biological datasets show consistent improvements over competitive baselines in the controlled generation of observational data and inference of biologically meaningful system inputs.

arXiv commentAccepted for the 38th Conference on Uncertainty in Artificial Intelligence (UAI 2022). Github code can be found at https://github.com/paidamoyo/structured_latent_ODEs

References in corpus (16)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• Semi-Supervised Learning with Deep Generative Models
• Variational Inference with Normalizing Flows
• Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
• Disentangling by Factorising
• Towards a Definition of Disentangled Representations
• GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
• Latent ODEs for Irregularly-Sampled Time Series
• Learning Disentangled Representations with Semi-Supervised Deep Generative Models
• Scalable Gradients for Stochastic Differential Equations
• A Disentangled Recognition and Nonlinear Dynamics Model for Unsupervised Learning
• ODE${}^2$VAE: Deep generative second order ODEs with Bayesian neural networks
• Disentangled Sequential Autoencoder
• Adaptive multi-channel event segmentation and feature extraction for monitoring health outcomes