Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction

Spatial-temporal prediction is a fundamental problem for constructing smart city, which is useful for tasks such as traffic control, taxi dispatching, and environment policy making. Due to data collection mechanism, it is common to see data collection with unbalanced spatial distributions. For example, some cities may release taxi data for multiple years while others only release a few days of data; some regions may have constant water quality data monitored by sensors whereas some regions only have a small collection of water samples. In this paper, we tackle the problem of spatial-temporal prediction for the cities with only a short period of data collection. We aim to utilize the long-period data from other cities via transfer learning. Different from previous studies that transfer knowledge from one single source city to a target city, we are the first to leverage information from multiple cities to increase the stability of transfer. Specifically, our proposed model is designed as a spatial-temporal network with a meta-learning paradigm. The meta-learning paradigm learns a well-generalized initialization of the spatial-temporal network, which can be effectively adapted to target cities. In addition, a pattern-based spatial-temporal memory is designed to distill long-term temporal information (i.e., periodicity). We conduct extensive experiments on two tasks: traffic (taxi and bike) prediction and water quality prediction. The experiments demonstrate the effectiveness of our proposed model over several competitive baseline models.

[1]  Rong Yan,et al.  Adapting SVM Classifiers to Data with Shifted Distributions , 2007, Seventh IEEE International Conference on Data Mining Workshops (ICDMW 2007).

[2]  Trevor Darrell,et al.  Adversarial Discriminative Domain Adaptation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Paolo Frasconi,et al.  Short-Term Traffic Flow Forecasting: An Experimental Comparison of Time-Series Analysis and Supervised Learning , 2013, IEEE Transactions on Intelligent Transportation Systems.

[4]  Gao Cong,et al.  An Experimental Evaluation of Point-of-interest Recommendation in Location-based Social Networks , 2017, Proc. VLDB Endow..

[5]  Lionel M. Ni,et al.  Time-Dependent Trajectory Regression on Road Networks via Multi-Task Learning , 2013, AAAI.

[6]  Feng Liu,et al.  Crowd Flow Prediction by Deep Spatio-Temporal Transfer Learning , 2018, ArXiv.

[7]  Rama Chellappa,et al.  Domain adaptation for object recognition: An unsupervised approach , 2011, 2011 International Conference on Computer Vision.

[8]  Xianfeng Tang,et al.  Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction , 2018, AAAI.

[9]  Enhong Chen,et al.  Incorporating Spatio-Temporal Smoothness for Air Quality Inference , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[10]  Wei Cao,et al.  DeepSD: Supply-Demand Prediction for Online Car-Hailing Services Using Deep Neural Networks , 2017, 2017 IEEE 33rd International Conference on Data Engineering (ICDE).

[11]  Masashi Sugiyama,et al.  Trajectory Regression on Road Networks , 2011, AAAI.

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

[13]  Richard S. Zemel,et al.  Prototypical Networks for Few-shot Learning , 2017, NIPS.

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

[15]  Jiliang Tang,et al.  Modeling Temporal-Spatial Correlations for Crime Prediction , 2017, CIKM.

[16]  Billy M. Williams,et al.  Adaptive Seasonal Time Series Models for Forecasting Short-Term Traffic Flow , 2007 .

[17]  Qiang Yang,et al.  EigenTransfer: a unified framework for transfer learning , 2009, ICML '09.

[18]  Hao Ma,et al.  GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs , 2018, UAI.

[19]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[20]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.

[21]  Jieping Ye,et al.  The Simpler The Better: A Unified Approach to Predicting Original Taxi Demands based on Large-Scale Online Platforms , 2017, KDD.

[22]  Hugo Larochelle,et al.  Optimization as a Model for Few-Shot Learning , 2016, ICLR.

[23]  Xiqun Chen,et al.  Short-Term Forecasting of Passenger Demand under On-Demand Ride Services: A Spatio-Temporal Deep Learning Approach , 2017, ArXiv.

[24]  Ugur Demiryurek,et al.  Deep Learning: A Generic Approach for Extreme Condition Traffic Forecasting , 2017, SDM.

[25]  Gao Cong,et al.  Efficient Similar Region Search with Deep Metric Learning , 2018, KDD.

[26]  Zhenhui Li,et al.  Region Representation Learning via Mobility Flow , 2017, CIKM.

[27]  Duo Zhang,et al.  Deep Learning for Real Time Crime Forecasting , 2017, ArXiv.

[28]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[29]  Zhanxing Zhu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017, IJCAI.

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

[31]  Richard J. Mammone,et al.  Meta-neural networks that learn by learning , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[32]  Yu Zhang,et al.  Transfer Learning via Learning to Transfer , 2018, ICML.

[33]  Yu Zheng,et al.  Deep Distributed Fusion Network for Air Quality Prediction , 2018, KDD.

[34]  Eunho Yang,et al.  Learning to Propagate Labels: Transductive Propagation Network for Few-Shot Learning , 2018, ICLR.

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

[36]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[37]  Zhenhui Li,et al.  IntelliLight: A Reinforcement Learning Approach for Intelligent Traffic Light Control , 2018, KDD.

[38]  Sergey Levine,et al.  Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks , 2017, ICML.

[39]  Feng Liu,et al.  Cross-City Transfer Learning for Deep Spatio-Temporal Prediction , 2018, IJCAI.

[40]  Christopher D. Manning,et al.  Effective Approaches to Attention-based Neural Machine Translation , 2015, EMNLP.

[41]  William-Chandra Tjhi,et al.  Dual Fuzzy-Possibilistic Co-clustering for Document Categorization , 2007 .

[42]  Qiang Yang,et al.  Transfer Knowledge between Cities , 2016, KDD.

[43]  Daniel Kifer,et al.  Non-Stationary Model for Crime Rate Inference Using Modern Urban Data , 2019, IEEE Transactions on Big Data.

[44]  Yuan Shi,et al.  Geodesic flow kernel for unsupervised domain adaptation , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[45]  Fei Wu,et al.  Interpreting traffic dynamics using ubiquitous urban data , 2016, SIGSPATIAL/GIS.

[46]  João Gama,et al.  Predicting Taxi–Passenger Demand Using Streaming Data , 2013, IEEE Transactions on Intelligent Transportation Systems.

[47]  Bin Yu,et al.  Spatio-temporal Graph Convolutional Neural Network: A Deep Learning Framework for Traffic Forecasting , 2017 .

[48]  Jiayu Zhou,et al.  GSpartan: a Geospatio-Temporal Multi-task Learning Framework for Multi-location Prediction , 2016, SDM.

[49]  Yi Yang,et al.  Transductive Propagation Network for Few-shot Learning , 2018, ArXiv.