Temporal Variational Implicit Neural Representations
This provides a computationally efficient and scalable solution for real-world time series applications, though it appears incremental as it builds on existing implicit neural representations and latent variable models.
The paper tackles the problem of modeling irregular multivariate time series for efficient individualized imputation and forecasting by introducing Temporal Variational Implicit Neural Representations (TV-INRs), achieving an order of magnitude improvement in mean squared error for imputation in low-data regimes.
We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient 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 methods by an order of magnitude in mean squared error for imputation task.