Subgraph-aware graph structure revision for spatial-temporal graph modeling
文献类型:期刊论文
作者 | Wang, Yuhu2,3; Zhang, Chunxia1; Xiang, Shiming2,3; Pan, Chunhong3 |
刊名 | NEURAL NETWORKS |
出版日期 | 2022-10-01 |
卷号 | 154页码:190-202 |
ISSN号 | 0893-6080 |
关键词 | Graph structure learning Graph neural network Spatial-temporal graph modeling |
DOI | 10.1016/j.neunet.2022.07.017 |
通讯作者 | Xiang, Shiming(smxiang@nlpr.ia.ac.cn) |
英文摘要 | Spatial-temporal graph modeling has been widely studied in many fields, such as traffic forecasting and energy analysis, where data has time and space properties. Existing methods focus on capturing stable and dynamic spatial correlations by constructing physical and virtual graphs along with graph convolution and temporal modeling. However, existing methods tending to smooth node features may obscure the spatial-temporal patterns among nodes. Worse, the graph structure is not always available in some fields, while the manually constructed stable or dynamic graphs cannot necessarily reflect the true spatial correlations either. This paper proposes a Subgraph-Aware Graph Structure Revision network (SAGSR) to overcome these limitations. Architecturally, a subgraph-aware structure revision graph convolution module (SASR-GCM) is designed, which revises the learned stable graph to obtain a dynamic one to automatically infer the dynamics of spatial correlations. Each of these two graphs is separated into one homophilic subgraph and one heterophilic subgraph by a subgraph-aware graph convolution mechanism, which aggregates similar nodes in the homophilic subgraph with positive weights, while keeping nodes with dissimilar features in the heterophilic subgraph mutually away with negative aggregation weights to avoid pattern obfuscation. By combining a gated multi-scale temporal convolution module (GMS-TCM) for temporal modeling, SAGSR can efficiently capture the spatial-temporal correlations and extract complex spatial-temporal graph features. Extensive experiments, conducted on two specific tasks: traffic flow forecasting and energy consumption forecasting, indicate the effectiveness and superiority of our proposed approach over several competitive baselines. (C) 2022 Elsevier Ltd. All rights reserved. |
WOS关键词 | CONVOLUTIONAL NETWORKS ; TRAFFIC FLOW |
资助项目 | National Key Research and Development Program of China[2020AAA0104903] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[62072039] ; National Natural Science Foundation of China[62076242] |
WOS研究方向 | Computer Science ; Neurosciences & Neurology |
语种 | 英语 |
出版者 | PERGAMON-ELSEVIER SCIENCE LTD |
WOS记录号 | WOS:000888516900009 |
资助机构 | National Key Research and Development Program of China ; National Natural Science Foundation of China |
源URL | [http://ir.ia.ac.cn/handle/173211/50782] |
专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
通讯作者 | Xiang, Shiming |
作者单位 | 1.Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 100081, Peoples R China 2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
推荐引用方式 GB/T 7714 | Wang, Yuhu,Zhang, Chunxia,Xiang, Shiming,et al. Subgraph-aware graph structure revision for spatial-temporal graph modeling[J]. NEURAL NETWORKS,2022,154:190-202. |
APA | Wang, Yuhu,Zhang, Chunxia,Xiang, Shiming,&Pan, Chunhong.(2022).Subgraph-aware graph structure revision for spatial-temporal graph modeling.NEURAL NETWORKS,154,190-202. |
MLA | Wang, Yuhu,et al."Subgraph-aware graph structure revision for spatial-temporal graph modeling".NEURAL NETWORKS 154(2022):190-202. |
入库方式: OAI收割
来源:自动化研究所
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。