.png){kind=icon}
返回
ClusterST: Clustering Spatial-Temporal Network for Traffic Forecasting
.png){kind=icon}
PRE
AI
DOI：10.1109/TITS.2022.3215703.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Traffic forecasting aims to capture complex spatial-temporal dependencies and non-linear dynamics, which plays an indispensable role in intelligent transportation systems and other domains like neuroscience, climate, etc. Most recent works rely on graph convolutional networks (GCN) to model the dependencies and the dynamics. However, the over-smoothing issue of GCN would produce indistinguishable features among nodes, leading to poor expressivity and weak capability of modeling complex dependencies and dynamics. To address this issue, we present a novel clustering spatial-temporal (ClusterST) unit, which incorporates unsupervised learning into GCN for extracting discriminative features. Specifically, we first exploit a neural network to learn a dynamic clustering, i.e., learning to partition the neighbors of each node into clusters at each time step. Two probabilistic losses are proposed to improve the separability of clusters. Then, the extracted features of different clusters can be distinguished. Based on the dynamically formed clusters, a vanilla GCN is applied to aggregate features within each cluster. By purely exploiting such a ClusterST unit, large improvements over the state-of-the-art are achieved. Furthermore, ClusterST units with a different number of clusters can be regarded as basic components to construct an inception-like ClusterST network for going deeper. We evaluate the framework on two real-world large-scale traffic datasets and observe an average improvement of $18.19\%$ and $7.62\%$ over state-of-the-art baselines, respectively. The code and models will be publicly available.
Keyword:
Index Terms- Traffic forecasting
graph convolutional network
spatial-temporal networks
over-smoothing
期刊
IF:
8.4
论文数:
9.7K
被引数:
6.3W
机构
引用论文
Isolated Giant Smooth Muscle Fibres in Beroe Ovata: Ionic Dependence of Action Potentials Reveals two Distinct Types of Fibre 卵子中的孤立的巨大平滑肌纤维: 动作电位的离子依赖性揭示了两种不同类型的纤维
.png){kind=icon}
PREAI
分享收藏Wide-Attention and Deep-Composite Model for Traffic Flow Prediction in Transportation Cyber-Physical Systems交通信息物理系统中交通流预测的广泛关注和深度复合模型
OAAI
OAAI分享收藏
查看更多内容