Time-Dependent Trajectory Regression on Road Networks via Multi-Task Learning
By Jiangchuan Zheng, Lionel Ming-shuan Ni. 2013
95 citations recorded by the source corpus.
Road travel costs are important knowledge hidden in large-scale GPS trajectory data sets, the discovery of which can benefit many applications such as intelligent route planning and automatic driving navigation. While there are previous studies which tackled this task by modeling it as a regression problem with spatial smoothness taken into account, they unreasonably assumed that the latent cost of each road remains unchanged over time. Other works on route planning and recommendation that have considered temporal factors simply assumed that the temporal dynamics be known in advance as a parametric function over time, which is not faithful to reality. To overcome these limitations, in this paper, we propose an extension to a previous static trajectory regression framework by learning the temporal dynamics of road travel costs in an innovative non-parametric manner which can effectively overcome the temporal sparsity problem. In particular, we unify multiple different trajectory regression problems in a multi-task framework by introducing a novel cross-task regularization which encourages temporal smoothness on the change of road travel costs. We then propose an efficient block coordinate descent method to solve the resulting problem by exploiting its separable structures and prove its convergence to global optimum. Experiments conducted on both synthetic and real data sets demonstrate the effectiveness of our method and its improved accuracy on travel time prediction.
Subfields: Building and Construction, Representation & Self-Supervised Learning, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Building and Construction
In Representation & Self-Supervised Learning
In Signal Processing
Citations in the corpus
- An Overview of Multi-task Learning (2018, background): “Applications of MTL in ubiquitous computing include stock prediction [126], multi-device localization [127], the inverse dynamics problem for robotics [128,129], estimation of travel costs on road networks [130], travel-time prediction on road networks [131], and traffic-sign recognition [132].”
- A Survey on Multi-Task Learning (2017, methodology): “In [211], a multi-task trajectory regression method, which encodes the spatial and temporal information via the Laplacian and fused Lasso regularizations, is proposed to estimate road travel costs on road”
- Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction (2018, methodology): “In addition, spatial information has also been explicitly modeled in recent studies (Deng et al. 2016; Tong et al. 2017; Idé and Sugiyama 2011; Zheng and Ni 2013).”
- A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation (2021, background): “Differently, the authors in [129] consider the temporal dynamic, which would learn different weights for different time slots.”
- Deep Multi-View Spatial-Temporal Network for Taxi Demand Prediction (2018, background): “Several studies (Tong et al. 2017; Id´e and Sugiyama 2011; Zheng and Ni 2013) also propose to smooth the prediction differences for nearby locations and time points via regularization for close space and time dependency.”
- Robust Dynamic Trajectory Regression on Road Networks: A Multi-task Learning Framework (2014, methodology): “Meanwhile, by solving a subproblem of quadratic programming for each decoupled row of W in every iteration, the per-iteration time complexity of DTRTS [5] is raised to O(n̄d2m3), which is much higher.”