ST-ExpertNet: A Deep Expert Framework for Traffic Prediction

Hongjun Wang1; Jiyuan Chen1; Zipei Fan2; Zhiwen Zhang2; Zekun Cai2; Xuan Song1

2022

10.1109/TKDE.2022.3196936

IEEE Transactions on Knowledge and Data Engineering   影响因子和分区

2326-3865

1558-2191

Recently, forecasting the crowd flows has become an important research topic, and plentiful technologies have achieved good performances. As we all know, the flow at a citywide level is in a mixed state with several basic patterns (e.g., commuting, working, and commercial) caused by the city area functional distributions (e.g., developed commercial areas, educational areas and parks). However, existing technologies have been criticized for their lack of considering the differences in the flow patterns among regions since they want to build only one comprehensive model to learn the mixed flow tensors. Recognizing this limitation, we present a new perspective on flow prediction and propose an explainable framework named ST-ExpertNet, which can adopt every spatial-temporal model and train a set of functional experts devoted to specific flow patterns. Technically, we train a bunch of experts based on the Mixture of Experts (MoE), which guides each expert to specialize in different kinds of flow patterns in sample spaces by using the gating network. We define several criteria, including comprehensiveness, sparsity, and preciseness, to construct the experts for better interpretability and performances. We conduct experiments on a wide range of real-world taxi and bike datasets in Beijing and NYC. The visualizations of the expert's intermediate results demonstrate that our ST-ExpertNet successfully disentangles the city's mixed flow tensors along with the city layout, e.g., the urban ring road structure. Different network architectures, such as ST-ResNet, ConvLSTM, and CNN, have been adopted into our ST-ExpertNet framework for experiments and the results demonstrates the superiority of our framework in both interpretability and performances.

Crowd flow prediction mixture of experts neural networks urban computing

EI ; SCI

英语

第一

Guangdong Provinial Key Laboratory[20K19782] ; Japan Society for the Promotion of Science, Japan's Ministry of Education, Culture, Sports, Science, and Technology (MEXT)[2020B121201001]

Computer Science ; Engineering

Computer Science, Artificial Intelligence ; Computer Science, Information Systems ; Engineering, Electrical & Electronic

WOS:001004293600071

IEEE COMPUTER SOC

20223412602136

Forecasting ; Job analysis ; Mixtures ; Network architecture ; Neural networks ; Parks ; Taxicabs ; Tensors

Fluid Flow, General:631.1 ; Automobiles:662.1 ; Algebra:921.1

ENGINEERING

IEEE

1.Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation, Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China
2.The University of Tokyo, Kashiwa-shi, Chiba, Japan

Hongjun Wang,Jiyuan Chen,Zipei Fan,et al. ST-ExpertNet: A Deep Expert Framework for Traffic Prediction[J]. IEEE Transactions on Knowledge and Data Engineering,2022,PP(99):1-14.

Hongjun Wang,Jiyuan Chen,Zipei Fan,Zhiwen Zhang,Zekun Cai,&Xuan Song.(2022).ST-ExpertNet: A Deep Expert Framework for Traffic Prediction.IEEE Transactions on Knowledge and Data Engineering,PP(99),1-14.

Hongjun Wang,et al."ST-ExpertNet: A Deep Expert Framework for Traffic Prediction".IEEE Transactions on Knowledge and Data Engineering PP.99(2022):1-14.