Time-Reversal Symmetric ODE Network
This work addresses the challenge of modeling complex physical dynamics for applications in mechanics and AI, representing an incremental improvement with a novel method for a known bottleneck.
The authors tackled the problem of learning physical system dynamics from noisy trajectories by proposing a novel loss function that enforces time-reversal symmetry in ODE networks, resulting in improved sample efficiency and better predictive performance compared to baselines.
Time-reversal symmetry, which requires that the dynamics of a system should not change with the reversal of time axis, is a fundamental property that frequently holds in classical and quantum mechanics. In this paper, we propose a novel loss function that measures how well our ordinary differential equation (ODE) networks comply with this time-reversal symmetry; it is formally defined by the discrepancy in the time evolutions of ODE networks between forward and backward dynamics. Then, we design a new framework, which we name as Time-Reversal Symmetric ODE Networks (TRS-ODENs), that can learn the dynamics of physical systems more sample-efficiently by learning with the proposed loss function. We evaluate TRS-ODENs on several classical dynamics, and find they can learn the desired time evolution from observed noisy and complex trajectories. We also show that, even for systems that do not possess the full time-reversal symmetry, TRS-ODENs can achieve better predictive performances over baselines.