Temporal Variational Implicit Neural Representations

Batuhan Koyuncu, Rachael DeVries, Ole Winther, Isabel Valera

Keywords: Time-series analysis, Generative Modeling, Implicit Neural Representations, Meta-learning

Abstract:

We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient and accurate individualized imputation and forecasting. By integrating implicit neural representations with latent variable models, TV-INRs learn distributions over time-continuous generator functions conditioned on signal-specific covariates.
Unlike existing approaches that require extensive training, fine-tuning or meta-learning, our method achieves accurate individualized predictions through a single forward pass. Our experiments demonstrate that with a single TV-INRs instance, we can accurately solve diverse imputation and forecasting tasks, offering a computationally efficient and scalable solution for real-world applications.
TV-INRs excel especially in low-data regimes, where it outperforms existing imputation methods by an order of magnitude in mean squared error.

Primary Area: generative models

Submission Number: 3711