Event-Aware Multimodal Mobility Nowcasting

As a decisive part in the success of Mobility-as-a-Service (MaaS), spatio-temporal predictive modeling for crowd movements is a challenging task particularly considering scenarios where societal events drive mobility behavior deviated from the normality. While tremendous progress has been made to model high-level spatio-temporal regularities with deep learning, most, if not all of the existing methods are neither aware of the dynamic interactions among multiple transport modes nor adaptive to unprecedented volatility brought by potential societal events. In this paper, we are therefore motivated to improve the canonical spatio-temporal network (ST-Net) from two perspectives: (1) design a heterogeneous mobility information network (HMIN) to explicitly represent intermodality in multimodal mobility; (2) propose a memory-augmented dynamic filter generator (MDFG) to generate sequence-specific parameters in an on-the-fly fashion for various scenarios. The enhanced event-aware spatiotemporal network, namely EAST-Net, is evaluated on several real-world datasets with a wide variety and coverage of societal events. Both quantitative and qualitative experimental results verify the superiority of our approach compared with the state-of-the-art baselines. Code and data are published on https://github.com/underdoc-wang/EAST-Net.

[1]  Cheng Wang,et al.  GMAN: A Graph Multi-Attention Network for Traffic Prediction , 2019, AAAI.

[2]  Yu Zheng,et al.  Detecting Urban Anomalies Using Multiple Spatio-Temporal Data Sources , 2018, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[3]  Gao Cong,et al.  Periodic-CRN: A Convolutional Recurrent Model for Crowd Density Prediction with Recurring Periodic Patterns , 2018, IJCAI.

[4]  Ryosuke Shibasaki,et al.  DeepUrbanEvent: A System for Predicting Citywide Crowd Dynamics at Big Events , 2019, KDD.

[5]  Junbo Zhang,et al.  Urban Traffic Prediction from Spatio-Temporal Data Using Deep Meta Learning , 2019, KDD.

[6]  Luc Van Gool,et al.  Dynamic Filter Networks , 2016, NIPS.

[7]  Hong Yu,et al.  Meta Networks , 2017, ICML.

[8]  Kai Zheng,et al.  Origin-Destination Matrix Prediction via Graph Convolution: a New Perspective of Passenger Demand Modeling , 2019, KDD.

[9]  Jing Jiang,et al.  Graph WaveNet for Deep Spatial-Temporal Graph Modeling , 2019, IJCAI.

[10]  Xiaojun Chang,et al.  Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks , 2020, KDD.

[11]  Xuan Song,et al.  Forecasting Ambulance Demand with Profiled Human Mobility via Heterogeneous Multi-Graph Neural Networks , 2021, 2021 IEEE 37th International Conference on Data Engineering (ICDE).

[12]  Qi Zhang,et al.  Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting , 2020, NeurIPS.

[13]  Quoc V. Le,et al.  HyperNetworks , 2016, ICLR.

[14]  Ryosuke Shibasaki,et al.  Decentralized Attention-based Personalized Human Mobility Prediction , 2019, Proc. ACM Interact. Mob. Wearable Ubiquitous Technol..

[15]  Sinno Jialin Pan,et al.  EnhanceNet: Plugin Neural Networks for Enhancing Correlated Time Series Forecasting , 2021, 2021 IEEE 37th International Conference on Data Engineering (ICDE).

[16]  Xuan Song,et al.  DeepUrbanMomentum: An Online Deep-Learning System for Short-Term Urban Mobility Prediction , 2018, AAAI.

[17]  Yanjie Fu,et al.  Co-Prediction of Multiple Transportation Demands Based on Deep Spatio-Temporal Neural Network , 2019, KDD.

[18]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[19]  Xuan Song,et al.  Prediction of human emergency behavior and their mobility following large-scale disaster , 2014, KDD.

[20]  Chao Zhang,et al.  DeepMove: Predicting Human Mobility with Attentional Recurrent Networks , 2018, WWW.

[21]  Yu Zheng,et al.  Deep Spatio-Temporal Residual Networks for Citywide Crowd Flows Prediction , 2016, AAAI.

[22]  Yongli Ren,et al.  MobTCast: Leveraging Auxiliary Trajectory Forecasting for Human Mobility Prediction , 2021, NeurIPS.

[23]  Martin Wattenberg,et al.  Stacked Graphs – Geometry & Aesthetics , 2008, IEEE Transactions on Visualization and Computer Graphics.

[24]  Quoc V. Le,et al.  CondConv: Conditionally Parameterized Convolutions for Efficient Inference , 2019, NeurIPS.

[25]  Ben Y. Zhao,et al.  Deep Graph Convolutional Networks for Incident-Driven Traffic Speed Prediction , 2020, CIKM.

[26]  Benjamin F. Grewe,et al.  Continual learning with hypernetworks , 2019, ICLR.

[27]  Pan Hui,et al.  A Decomposition Approach for Urban Anomaly Detection Across Spatiotemporal Data , 2019, IJCAI.

[28]  Xianfeng Tang,et al.  Joint Modeling of Local and Global Temporal Dynamics for Multivariate Time Series Forecasting with Missing Values , 2019, AAAI.

[29]  Masamichi Shimosaka,et al.  CityProphet: city-scale irregularity prediction using transit app logs , 2016, UbiComp.

[30]  Xuan Song,et al.  Countrywide Origin-Destination Matrix Prediction and Its Application for COVID-19 , 2021, ECML/PKDD.

[31]  Xuan Song,et al.  CityMomentum: an online approach for crowd behavior prediction at a citywide level , 2015, UbiComp.

[32]  Varun Jampani,et al.  Decoupled Dynamic Filter Networks , 2021, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[33]  Jieping Ye,et al.  Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction , 2018, AAAI.

[34]  Xianfeng Tang,et al.  Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction , 2019, WWW.

[35]  Dit-Yan Yeung,et al.  Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting , 2015, NIPS.

[36]  Cyrus Shahabi,et al.  Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting , 2017, ICLR.

[37]  Wenhu Chen,et al.  Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting , 2019, NeurIPS.

[38]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.