Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913390402732032 |
|---|---|
| author | Liu, Haoxin Kamarthi, Harshavardhan Kong, Lingkai Zhao, Zhiyuan Zhang, Chao Prakash, B. Aditya |
| author_facet | Liu, Haoxin Kamarthi, Harshavardhan Kong, Lingkai Zhao, Zhiyuan Zhang, Chao Prakash, B. Aditya |
| contents | Time-series forecasting (TSF) finds broad applications in real-world scenarios. Due to the dynamic nature of time-series data, it is crucial to equip TSF models with out-of-distribution (OOD) generalization abilities, as historical training data and future test data can have different distributions. In this paper, we aim to alleviate the inherent OOD problem in TSF via invariant learning. We identify fundamental challenges of invariant learning for TSF. First, the target variables in TSF may not be sufficiently determined by the input due to unobserved core variables in TSF, breaking the conventional assumption of invariant learning. Second, time-series datasets lack adequate environment labels, while existing environmental inference methods are not suitable for TSF.
To address these challenges, we propose FOIL, a model-agnostic framework that enables timeseries Forecasting for Out-of-distribution generalization via Invariant Learning. FOIL employs a novel surrogate loss to mitigate the impact of unobserved variables. Further, FOIL implements a joint optimization by alternately inferring environments effectively with a multi-head network while preserving the temporal adjacency structure, and learning invariant representations across inferred environments for OOD generalized TSF. We demonstrate that the proposed FOIL significantly improves the performance of various TSF models, achieving gains of up to 85%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09130 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning Liu, Haoxin Kamarthi, Harshavardhan Kong, Lingkai Zhao, Zhiyuan Zhang, Chao Prakash, B. Aditya Machine Learning Artificial Intelligence H.0 Time-series forecasting (TSF) finds broad applications in real-world scenarios. Due to the dynamic nature of time-series data, it is crucial to equip TSF models with out-of-distribution (OOD) generalization abilities, as historical training data and future test data can have different distributions. In this paper, we aim to alleviate the inherent OOD problem in TSF via invariant learning. We identify fundamental challenges of invariant learning for TSF. First, the target variables in TSF may not be sufficiently determined by the input due to unobserved core variables in TSF, breaking the conventional assumption of invariant learning. Second, time-series datasets lack adequate environment labels, while existing environmental inference methods are not suitable for TSF. To address these challenges, we propose FOIL, a model-agnostic framework that enables timeseries Forecasting for Out-of-distribution generalization via Invariant Learning. FOIL employs a novel surrogate loss to mitigate the impact of unobserved variables. Further, FOIL implements a joint optimization by alternately inferring environments effectively with a multi-head network while preserving the temporal adjacency structure, and learning invariant representations across inferred environments for OOD generalized TSF. We demonstrate that the proposed FOIL significantly improves the performance of various TSF models, achieving gains of up to 85%. |
| title | Time-Series Forecasting for Out-of-Distribution Generalization Using Invariant Learning |
| topic | Machine Learning Artificial Intelligence H.0 |
| url | https://arxiv.org/abs/2406.09130 |