Meta Graph Transformer: A Novel Framework for Spatial-Temporal Traffic Prediction
文献类型：期刊论文
| 作者 | Ye, Xue3,4 ; Fang, Shen3,4; Sun, Fang2; Zhang, Chunxia1; Xiang, Shiming3,4
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2022-06-28 |
| 卷号 | 491页码:544-563 |
| 关键词 | Traffic prediction Spatial-temporal modeling Meta-learning Attention mechanism Deep learning |
| ISSN号 | 0925-2312 |
| DOI | 10.1016/j.neucom.2021.12.033 |
| 通讯作者 | Ye, Xue(xue.ye@nlpr.ia.ac.cn) |
| 英文摘要 | Accurate traffic prediction is critical for enhancing the performance of intelligent transportation systems. The key challenge to this task is how to properly model the complex dynamics of traffic while respecting and exploiting both spatial and temporal heterogeneity in data. This paper proposes a novel framework called Meta Graph Transformer (MGT) to address this problem. The MGT framework is a generalization of the original transformer, which is used to model vector sequences in natural language processing. Specifically, MGT has an encoder-decoder architecture. The encoder is responsible for encoding historical traffic data into intermediate representations, while the decoder predicts future traffic states autoregressively. The main building blocks of MGT are three types of attention layers named Temporal SelfAttention (TSA), Spatial Self-Attention (SSA), and Temporal Encoder-Decoder Attention (TEDA), respectively. They all have a multi-head structure. TSAs and SSAs are employed by both the encoder and decoder to capture temporal and spatial correlations. TEDAs are employed by the decoder, allowing every position in the decoder to attend all positions in the input sequence temporally. By leveraging multiple graphs, SSA can conduct sparse spatial attention with various inductive biases. To facilitate the model's awareness of temporal and spatial conditions, Spatial-Temporal Embeddings (STEs) are learned from external attributes, which are composed of temporal attributes (e.g. sequential order, time of day) and spatial attributes (e.g. Laplacian eigenmaps). These embeddings are then utilized by all the attention layers via meta-learning, hence endowing these layers with Spatial-Temporal Heterogeneity-Aware (STHA) properties. Experiments on three real-world traffic datasets demonstrate the superiority of our model over several state-of-the-art methods. Our code and data are available at (http://github.com/lonicera-yx/MGT). (C) 2021 Elsevier B.V. All rights reserved. |
| WOS关键词 | NEURAL-NETWORKS ; FLOW PREDICTION ; MODEL |
| 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 |
| 语种 | 英语 |
| WOS记录号 | WOS:000830181200012 |
| 出版者 | ELSEVIER |
| 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/173211/49797]  |
| 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 | Ye, Xue |
| 作者单位 | 1.Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 100081, Peoples R China 2.Capital Normal Univ, Sch Math Sci, Beijing 100048, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Ye, Xue,Fang, Shen,Sun, Fang,et al. Meta Graph Transformer: A Novel Framework for Spatial-Temporal Traffic Prediction[J]. NEUROCOMPUTING,2022,491:544-563. |
| APA | Ye, Xue,Fang, Shen,Sun, Fang,Zhang, Chunxia,&Xiang, Shiming.(2022).Meta Graph Transformer: A Novel Framework for Spatial-Temporal Traffic Prediction.NEUROCOMPUTING,491,544-563. |
| MLA | Ye, Xue,et al."Meta Graph Transformer: A Novel Framework for Spatial-Temporal Traffic Prediction".NEUROCOMPUTING 491(2022):544-563. |
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。