Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917261181190144 |
|---|---|
| author | Naour, Etienne Le Serrano, Louis Migus, Léon Yin, Yuan Agoua, Ghislain Baskiotis, Nicolas Gallinari, Patrick Guigue, Vincent |
| author_facet | Naour, Etienne Le Serrano, Louis Migus, Léon Yin, Yuan Agoua, Ghislain Baskiotis, Nicolas Gallinari, Patrick Guigue, Vincent |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_05880 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations Naour, Etienne Le Serrano, Louis Migus, Léon Yin, Yuan Agoua, Ghislain Baskiotis, Nicolas Gallinari, Patrick Guigue, Vincent Machine Learning Artificial Intelligence 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. |
| title | Time Series Continuous Modeling for Imputation and Forecasting with Implicit Neural Representations |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2306.05880 |