Learning to Decouple Complex System for Sequential Data

Zihan Zhou, Minxin Ao, Tianshu Yu

Keywords: neural differential equation, sequential learning, decoupling complex system

TL;DR: We propose to learn to decouple a complex system into simple but interacting latent sub-systems, which proved effective and powerful in sequential modeling.

Abstract: A complex system with cluttered observations may be a coupled mixture of multiple simple sub-systems corresponding to \emph{latent entities}. Such sub-systems may hold distinct dynamics in the continuous-time domain, therein complicated interactions between sub-systems also evolve over time. This setting is fairly common in the real world, but has been less considered. In this paper, we propose a sequential learning approach under this setting by decoupling a complex system for handling irregularly sampled and cluttered sequential observations. Such decoupling brings about not only subsystems describing the dynamics of each latent entity, but also a meta-system capturing the interaction between entities over time. Specifically, we argue that the meta-system of interactions is governed by a smoothed version of \emph{projected differential equations}. Experimental results on synthetic and real-world datasets show the advantages of our approach when facing complex and cluttered sequential data compared to the state-of-the-art.

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: Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability )