基于自注意力机制与图自编码器的路网交通流数据修复模型

针对城市交通流数据修复问题,提出一种基于图卷积网络和多头自注意力机制的自注意力图自编码器模型.该模型包括基于拓扑图结构和图信号捕获交通流时空关联性的STGCN(Spatial-temporal Graph Convolutional Networks)网络.在该网络中使用LSTM(Long Short-Term Mem...

Missing Data Repairs for Road Network Traffic Flow with Self-attention Graph Auto-encoder Networks

Focusing on the urban traffic flow imputation problem, this paper proposes a self- attention graphautoencoder (SA- GAE, Self- Attention Graph Auto- Encoder) based on the Graph Convolutional Networks andMultihead-Attention. The model includes the STGCN (Spatial-temporal Graph Convolutional Networks) networkwhich captures the spatial- temporal correlation of traffic flow based on the topological graph structures and graphsignals. In this network, the LSTM (Long Short-Term Memory) network is used to learn the temporal relationship inthe data, the road self-attention and the first- order adjacent road attention coefficient are calculated through the roadattention network, and the graph signal is reorganized by the graph convolution network to achieve the goal of preciseimputation of missing data. The Multihead-Attention network is used to calculate the attention weight of the data andreorganize the data. The Multihead-Attention network can capture the spatial correlation in the second-order and highorder neighbor road traffic flow data and extract the relationship between the known data after the missing period andthe missing data. The time relationship is added to the model in the form of residual chain as a supplement to thefunction of the STGCN. Experiments show that in multiple missing mode scenarios, the model can learn thetopological relationship of road network, capture the temporal regularity in traffic data, understand the temporal andspatial correlations contained, and effectively repair the missing parts of the data.