MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data
文献类型：期刊论文
| 作者 | Zhou, Jianping3; Bin Lu3; Liu, Zhanyu3; Pan, Siyu3; Feng, Xuejun3; Wei, Hua1; Zheng, Guanjie3; Wang, Xinbing3; Zhou, Chenghu2 |
| 刊名 | ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA
 |
| 出版日期 | 4587 |
| 卷号 | 19期号:7页码:130 |
| 关键词 | Traffic Data Imputation Graph Neural Network |
| ISSN号 | 1556-4681 |
| DOI | 10.1145/3743141 |
| 产权排序 | 3 |
| 文献子类 | Article |
| 英文摘要 | Due to detector malfunctions and communication failures, missing data is ubiquitous during the collection of traffic data. Therefore, it is of vital importance to impute the missing values to facilitate data analysis and decision-making for Intelligent Transportation System (ITS). However, existing imputation methods generally perform zero pre-filling techniques to initialize missing values, introducing inevitable noise. Moreover, we observe prevalent over-smoothed interpolations, falling short in revealing the intrinsic spatio-temporal correlations of incomplete traffic data. To this end, we propose Mask-Aware Graph Imputation Network (MagiNet). Our method designs an adaptive mask spatio-temporal encoder to learn the latent representations of incomplete data, eliminating the reliance on pre-filling missing values. Furthermore, we devise a spatio-temporal decoder that stacks multiple blocks to capture the inherent spatial and temporal dependencies within incomplete traffic data, alleviating over-smoothed imputation. Extensive experiments demonstrate that our method outperforms state-of-the-art imputation methods on five real-world traffic datasets, yielding an average improvement of 4.31% in RMSE and 3.72% in MAPE under Missing Completely at Random (MCAR) pattern. Code is available at https://github.com/JeremyChou28/MagiNet. |
| URL标识 | 查看原文 |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:001638936100005 |
| 出版者 | ASSOC COMPUTING MACHINERY |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/219420]  |
| 专题 | 资源与环境信息系统国家重点实验室_外文论文 |
| 通讯作者 | Zheng, Guanjie |
| 作者单位 | 1.Arizona State Univ, Tempe, AZ USA; 2.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing, Peoples R China 3.Shanghai Jiao Tong Univ, Shanghai, Peoples R China; |
| 推荐引用方式 GB/T 7714 | Zhou, Jianping,Bin Lu,Liu, Zhanyu,et al. MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data[J]. ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,4587,19(7):130. |
| APA | Zhou, Jianping.,Bin Lu.,Liu, Zhanyu.,Pan, Siyu.,Feng, Xuejun.,...&Zhou, Chenghu.(4587).MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data.ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA,19(7),130. |
| MLA | Zhou, Jianping,et al."MagiNet: Mask-Aware Graph Imputation Network for Incomplete Traffic Data".ACM TRANSACTIONS ON KNOWLEDGE DISCOVERY FROM DATA 19.7(4587):130. |
入库方式： OAI收割
来源：地理科学与资源研究所
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。