Predicting Collective Human Mobility via Countering Spatiotemporal Heterogeneity
- 18 July 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 23 (5) , 4723-4738
Abstract
Human mobility forecasting is the key to energizing considerable mobile computing services. However, we find that the collective mobility suffers the spatiotemporal heterogeneity issue and therefore leads to inferior performances of conventional homogeneous aggregations. Given two fundamental factors, i.e., data and objectives in machine learning, we propose to counter such heterogeneity by improving data utilization and optimization objectives. 1) From data utilization perspective, we discover that such heterogeneity is inherently induced by mobility-related context factors and thus these factors can be exploited to learn heterogeneous mobility patterns. 2) From the optimization perspective, the dependencies among output elements, which give another prior to learning, can extract heterogeneous correlations within output sequences. Specifically, we propose a novel Context-Directional SpatioTemporal Graph Network (CD-STGNet), which tackles the above-mentioned heterogeneity, for achieving accurate mobility predictions. First, we improve data utilization by inputting the encoded context-wise interactions to a direction field learner, which realizes directional spatial aggregations. Second, regarding series learning and optimization objectives, a context-trend highway is designed to enable context-aware temporal learning while two regularization objectives are proposed to keep the correlations among predicted elements consistent with the ground-truth. Experiments demonstrate that CD-STGNet surpasses competitive baselines by 13% to 22% and boosts the interpretability of context-directional learning.Keywords
Funding Information
- National Natural Science Foundation of China (62072427)
- National Natural Science Foundation of China (12227901)
- National Natural Science Foundation of China (62271452)
- Youth Team in Basic Research Field, CAS (YSBR-005)
- National Key Research and Development Program of China (2022YFB4500300)
- Key Research Project of Zhejiang Lab (2022PI0AC01)
This publication has 44 references indexed in Scilit:
- Graph neural network for traffic forecasting: A surveyExpert Systems with Applications, 2022
- Deep spatial–temporal sequence modeling for multi-step passenger demand predictionFuture Generation Computer Systems, 2021
- A spatiotemporal deep learning approach for citywide short-term crash risk prediction with multi-source dataAccident Analysis & Prevention, 2019
- Modeling Relational Data with Graph Convolutional Networks2018
- Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation2016
- A Realistic and Optimized V2V Communication System for Taxicabs2016
- A traffic congestion detection and information dissemination scheme for urban expressways using vehicular networksTransportation Research Part C: Emerging Technologies, 2014
- Interdependence and predictability of human mobility and social interactionsPervasive and Mobile Computing, 2013
- Approaching the Limit of Predictability in Human MobilityScientific Reports, 2013
- A coordinate gradient descent method for nonsmooth separable minimizationMathematical Programming, 2007