Jinglei Pei
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jinglei Pei has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Jingbin Yang
Institute of Computing Technology, University of Chinese Academy of Sciences, Beijing 100190, China
1 shared publication - Kang Qin
SINOPEC Research Institute of Petroleum Processing CO., Ltd., SINOPEC
1 shared publication - Qinghua Wu
University of Chinese Academy of Sciences
1 shared publication - Ting Liu
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China
1 shared publication - Yang Zhang
Research Institute of Petroleum Processing, SINOPEC, Beijing 100083, China
1 shared publication
Latest Publications
- Open Access
- 17 April 2025
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 7 (2) , 35
ADTime: Adaptive Multivariate Time Series Forecasting Using LLMs
Large language models (LLMs) have recently demonstrated notable performance, particularly in addressing the challenge of extensive data requirements when training traditional forecasting models. However, these methods encounter significant challenges when applied to high-dimensional and domain-specific datasets. These challenges primarily arise from inability to effectively model inter-variable dependencies and capture variable-specific characteristics, leading to suboptimal performance in complex forecasting scenarios. To address these limitations, we propose ADTime, an adaptive LLM-based approach for multivariate time series forecasting. ADTime employs advanced preprocessing techniques to identify latent relationships among key variables and temporal features. Additionally, it integrates temporal alignment mechanisms and prompt-based strategies to enhance the semantic understanding of forecasting tasks by LLMs. Experimental results show that ADTime outperforms state-of-the-art methods, reducing MSE by 9.5% and MAE by 6.1% on public datasets, and by 17.1% and 13.5% on domain-specific datasets. Furthermore, zero-shot experiments on real-world refinery datasets demonstrate that ADTime exhibits stronger generalization capabilities across various transfer scenarios. These findings highlight the potential of ADTime in advancing complex, domain-specific time series forecasting tasks.
- 17 April 2025
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 7 (2) , 35
Open AccessADTime: Adaptive Multivariate Time Series Forecasting Using LLMs
Large language models (LLMs) have recently demonstrated notable performance, particularly in addressing the challenge of extensive data requirements when training traditional forecasting models. However, these methods encounter significant challenges when applied to high-dimensional and domain-specific datasets. These challenges primarily arise from inability to effectively model inter-variable dependencies and capture variable-specific characteristics, leading to suboptimal performance in complex forecasting scenarios. To address these limitations, we propose ADTime, an adaptive LLM-based approach for multivariate time series forecasting. ADTime employs advanced preprocessing techniques to identify latent relationships among key variables and temporal features. Additionally, it integrates temporal alignment mechanisms and prompt-based strategies to enhance the semantic understanding of forecasting tasks by LLMs. Experimental results show that ADTime outperforms state-of-the-art methods, reducing MSE by 9.5% and MAE by 6.1% on public datasets, and by 17.1% and 13.5% on domain-specific datasets. Furthermore, zero-shot experiments on real-world refinery datasets demonstrate that ADTime exhibits stronger generalization capabilities across various transfer scenarios. These findings highlight the potential of ADTime in advancing complex, domain-specific time series forecasting tasks.