Koopman Operator Identification of Model Parameter Trajectories for Temporal Domain Generalization (KOMET)
For machine learning models deployed in temporally drifting environments, KOMET provides a zero-retraining adaptation method that predicts parameter evolution, enabling continuous deployment without access to future labeled data.
KOMET treats parameter trajectories of models in non-stationary environments as a dynamical system, using Koopman operator theory to predict future parameters without retraining, achieving mean autonomous-rollout accuracies between 0.981 and 1.000 over 100 time steps across six datasets.
Parametric models deployed in non-stationary environments degrade as the underlying data distribution evolves over time (a phenomenon known as temporal domain drift). In the current work, we present KOMET (Koopman Operator identification of Model parameter Evolution under Temporal drift), a model-agnostic, data-driven framework that treats the sequence of trained parameter vectors as the trajectory of a nonlinear dynamical system and identifies its governing linear operator via Extended Dynamic Mode Decomposition (EDMD). A warm-start sequential training protocol enforces parameter-trajectory smoothness, and a Fourier-augmented observable dictionary exploits the periodic structure inherent in many real-world distribution drifts. Once identified, KOMET's Koopman operator predicts future parameter trajectories autonomously, without access to future labeled data, enabling zero-retraining adaptation at deployment. Evaluated on six datasets spanning rotating, oscillating, and expanding distribution geometries, KOMET achieves mean autonomous-rollout accuracies between 0.981 and 1.000 over 100 held-out time steps. Spectral and coupling analyses further reveal interpretable dynamical structure consistent with the geometry of the drifting decision boundary.