Neural Constraint Inference: Inferring Energy Constraints in Interacting Systems

Armand Comas, Yilun Du, Sandesh Ghimire, Christian Fernandez Lopez, Mario Sznaier, Joshua B. Tenenbaum, Octavia Camps

Keywords: relational inference, energy-based models, energy constraints, trajectory prediction, graph neural networks

TL;DR: We propose an approach that discovers a set of relational constraints, represented as energy functions, which when optimized reconstruct a given original trajectory.

Abstract: Systems consisting of interacting agents are prevalent in the world, ranging from dynamical systems in physics to complex biological networks. To build systems which can interact robustly in the real world, it is thus important to be able to infer the precise interactions governing such systems. Existing approaches typically discover such interactions by explicitly modeling the feedforward dynamics of the trajectories. In this work, we propose Neural Constraint Inference (NCI) model as an alternative approach to discover such interactions: it discovers a set of relational constraints, represented as energy functions, which when optimized reconstruct the original trajectory. We illustrate how NCI can faithfully predict future trajectory dynamics, achieving more consistent long-rollouts than existing approaches. We show that the constraints discovered by NCI are disentangled and may be intermixed with constraints from other trajectories. Finally, we illustrate how those constraints enable the incorporation of external test-time constraints.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Unsupervised and Self-supervised learning