TSI-Bench: Benchmarking Time Series Imputation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909373614260224 |
|---|---|
| author | Du, Wenjie Wang, Jun Qian, Linglong Yang, Yiyuan Ibrahim, Zina Liu, Fanxing Wang, Zepu Liu, Haoxin Zhao, Zhiyuan Zhou, Yingjie Wang, Wenjia Ding, Kaize Liang, Yuxuan Prakash, B. Aditya Wen, Qingsong |
| author_facet | Du, Wenjie Wang, Jun Qian, Linglong Yang, Yiyuan Ibrahim, Zina Liu, Fanxing Wang, Zepu Liu, Haoxin Zhao, Zhiyuan Zhou, Yingjie Wang, Wenjia Ding, Kaize Liang, Yuxuan Prakash, B. Aditya Wen, Qingsong |
| contents | Effective imputation is a crucial preprocessing step for time series analysis. Despite the development of numerous deep learning algorithms for time series imputation, the community lacks standardized and comprehensive benchmark platforms to effectively evaluate imputation performance across different settings. Moreover, although many deep learning forecasting algorithms have demonstrated excellent performance, whether their modelling achievements can be transferred to time series imputation tasks remains unexplored. To bridge these gaps, we develop TSI-Bench, the first (to our knowledge) comprehensive benchmark suite for time series imputation utilizing deep learning techniques. The TSI-Bench pipeline standardizes experimental settings to enable fair evaluation of imputation algorithms and identification of meaningful insights into the influence of domain-appropriate missing rates and patterns on model performance. Furthermore, TSI-Bench innovatively provides a systematic paradigm to tailor time series forecasting algorithms for imputation purposes. Our extensive study across 34,804 experiments, 28 algorithms, and 8 datasets with diverse missingness scenarios demonstrates TSI-Bench's effectiveness in diverse downstream tasks and potential to unlock future directions in time series imputation research and analysis. All source code and experiment logs are released at https://github.com/WenjieDu/AwesomeImputation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_12747 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | TSI-Bench: Benchmarking Time Series Imputation Du, Wenjie Wang, Jun Qian, Linglong Yang, Yiyuan Ibrahim, Zina Liu, Fanxing Wang, Zepu Liu, Haoxin Zhao, Zhiyuan Zhou, Yingjie Wang, Wenjia Ding, Kaize Liang, Yuxuan Prakash, B. Aditya Wen, Qingsong Machine Learning Artificial Intelligence Effective imputation is a crucial preprocessing step for time series analysis. Despite the development of numerous deep learning algorithms for time series imputation, the community lacks standardized and comprehensive benchmark platforms to effectively evaluate imputation performance across different settings. Moreover, although many deep learning forecasting algorithms have demonstrated excellent performance, whether their modelling achievements can be transferred to time series imputation tasks remains unexplored. To bridge these gaps, we develop TSI-Bench, the first (to our knowledge) comprehensive benchmark suite for time series imputation utilizing deep learning techniques. The TSI-Bench pipeline standardizes experimental settings to enable fair evaluation of imputation algorithms and identification of meaningful insights into the influence of domain-appropriate missing rates and patterns on model performance. Furthermore, TSI-Bench innovatively provides a systematic paradigm to tailor time series forecasting algorithms for imputation purposes. Our extensive study across 34,804 experiments, 28 algorithms, and 8 datasets with diverse missingness scenarios demonstrates TSI-Bench's effectiveness in diverse downstream tasks and potential to unlock future directions in time series imputation research and analysis. All source code and experiment logs are released at https://github.com/WenjieDu/AwesomeImputation. |
| title | TSI-Bench: Benchmarking Time Series Imputation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2406.12747 |