Beyond Predictions in Neural ODEs: Identification and Interventions
This addresses the challenge of scientific discovery from data for researchers in fields like physics or biology, though it appears incremental as it builds on existing neural ODE methods.
The paper tackled the problem of uncovering governing ordinary differential equations (ODDEs) and causal structures from observational time-series data, showing that combining regularization with neural ODEs robustly recovers dynamics and enables accurate predictions under interventions.
Spurred by tremendous success in pattern matching and prediction tasks, researchers increasingly resort to machine learning to aid original scientific discovery. Given large amounts of observational data about a system, can we uncover the rules that govern its evolution? Solving this task holds the great promise of fully understanding the causal interactions and being able to make reliable predictions about the system's behavior under interventions. We take a step towards answering this question for time-series data generated from systems of ordinary differential equations (ODEs). While the governing ODEs might not be identifiable from data alone, we show that combining simple regularization schemes with flexible neural ODEs can robustly recover the dynamics and causal structures from time-series data. Our results on a variety of (non)-linear first and second order systems as well as real data validate our method. We conclude by showing that we can also make accurate predictions under interventions on variables or the system itself.