Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations
arXiv:2306.05880
Abstract
We introduce a novel modeling approach for time series imputation and forecasting, tailored to address the challenges often encountered in real-world data, such as irregular samples, missing data, or unaligned measurements from multiple sensors. Our method relies on a continuous-time-dependent model of the series' evolution dynamics. It leverages adaptations of conditional, implicit neural representations for sequential data. A modulation mechanism, driven by a meta-learning algorithm, allows adaptation to unseen samples and extrapolation beyond observed time-windows for long-term predictions. The model provides a highly flexible and unified framework for imputation and forecasting tasks across a wide range of challenging scenarios. It achieves state-of-the-art performance on classical benchmarks and outperforms alternative time-continuous models.
References in corpus (16)
- XGBoost: A Scalable Tree Boosting System
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains
- A Time Series is Worth 64 Words: Long-term Forecasting with Transformers
- SAITS: Self-Attention-based Imputation for Time Series
- FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
- BRITS: Bidirectional Recurrent Imputation for Time Series
- Fast Context Adaptation via Meta-Learning
- GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
- Latent ODEs for Irregularly-Sampled Time Series
- From data to functa: Your data point is a function and you can treat it like one
- Continuous PDE Dynamics Forecasting with Implicit Neural Representations
- HyperTime: Implicit Neural Representation for Time Series
- Modeling Temporal Data as Continuous Functions with Stochastic Process Diffusion
- Time-Series Anomaly Detection with Implicit Neural Representation
- Compressing multidimensional weather and climate data into neural networks