中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
GinAR plus : A Robust End-to-End Framework for Multivariate Time Series Forecasting With Missing Values

文献类型：期刊论文

作者Yu, Chengqing1,2; Wang, Fei1,2; Shao, Zezhi3; Qian, Tangwen3; Zhang, Zhao3; Wei, Wei4; An, Zhulin3; Wang, Qi3; Xu, Yongjun1,2
刊名IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
出版日期2025-08-01
卷号37期号:8页码:4635-4648
关键词Correlation Predictive models Forecasting Time series analysis Data models Robustness Adaptation models Imputation Contrastive learning Training graph interpolation attention recursive network multivariate time series forecasting with missing values
ISSN号1041-4347
DOI10.1109/TKDE.2025.3569649
英文摘要Spatial-Temporal Graph Neural Networks (STGNNs) have been widely utilized in multivariate time series forecasting (MTSF), but they rely on the assumption of data completeness. In practice, due to factors such as natural disaster, STGNNs frequently encounter the challenge of missing data resulting from numerous malfunctioning data collectors. In this case, on the one hand, due to the presence of missing values, STGNNs easily generate incorrect spatial correlations, leading to the performance degradation. On the other hand, STGNNs require separate training of models for different missing rates, limiting their robustness. To address these challenges, we first propose two important components (interpolation attention and adaptive graph convolution), which utilize normal values to recover missing values into reliable representations and reconstruct spatial correlations. Then, we replace the fully connected layers in simple recursive units with these two components and propose Graph Interpolation Attention Recursive Network (GinAR), aiming to recursively correct spatial correlations and achieve end-to-end MTSF with missing values. Finally, we use data with different missing rates as positive and negative data pairs. By employing contrastive learning to train GinAR, we propose GinAR+ and enhance its robustness to data with different missing rates. Experiments validate the superiority of GinAR+ and our motivation.
资助项目NSFC[62372430] ; CPSF[GZC20241758] ; Youth Innovation Promotion Association CAS[2023112]
WOS研究方向Computer Science ; Engineering
语种英语
WOS记录号WOS:001525525600027
出版者IEEE COMPUTER SOC
源URL[http://119.78.100.204/handle/2XEOYT63/42042]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Wang, Fei
作者单位1.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
3.Chinese Acad Sci, Inst Comp Technol, Beijing 100190, Peoples R China
4.Huazhong Univ Sci & Technol, Sch Comp Sci & Technol, Wuhan 430074, Peoples R China
推荐引用方式
GB/T 7714		 Yu, Chengqing,Wang, Fei,Shao, Zezhi,et al. GinAR plus : A Robust End-to-End Framework for Multivariate Time Series Forecasting With Missing Values[J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,2025,37(8):4635-4648.
APA Yu, Chengqing.,Wang, Fei.,Shao, Zezhi.,Qian, Tangwen.,Zhang, Zhao.,...&Xu, Yongjun.(2025).GinAR plus : A Robust End-to-End Framework for Multivariate Time Series Forecasting With Missing Values.IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING,37(8),4635-4648.
MLA Yu, Chengqing,et al."GinAR plus : A Robust End-to-End Framework for Multivariate Time Series Forecasting With Missing Values".IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 37.8(2025):4635-4648.

入库方式： OAI收割

来源：计算技术研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。