Multi-task Learning for Sparse Traffic Forecasting

• URL: http://arxiv.org/abs/2211.09984v1
• Date: Fri, 18 Nov 2022 02:10:40 GMT
• Title: Multi-task Learning for Sparse Traffic Forecasting
• Authors: Jiezhang Li, Junjun Li, Yue-Jiao Gong
• Abstract summary: We propose a multi-task learning network that can simultaneously predict the congestion classes and the speed of each road segment. Our method achieved excellent results on the dataset provided by the Traffic4cast Competition 2022, source code is available at https://github.com/OctopusLi/NeurIPS2022-traffic4cast.
• Score: 13.359590890052454
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate traffic prediction is crucial to improve the performance of intelligent transportation systems. Previous traffic prediction tasks mainly focus on small and non-isolated traffic subsystems, while the Traffic4cast 2022 competition is dedicated to exploring the traffic state dynamics of entire cities. Given one hour of sparse loop count data only, the task is to predict the congestion classes for all road segments and the expected times of arrival along super-segments 15 minutes into the future. The sparsity of loop counter data and highly uncertain real-time traffic conditions make the competition challenging. For this reason, we propose a multi-task learning network that can simultaneously predict the congestion classes and the speed of each road segment. Specifically, we use clustering and neural network methods to learn the dynamic features of loop counter data. Then, we construct a graph with road segments as nodes and capture the spatial dependence between road segments based on a Graph Neural Network. Finally, we learn three measures, namely the congestion class, the speed value and the volume class, simultaneously through a multi-task learning module. For the extended competition, we use the predicted speeds to calculate the expected times of arrival along super-segments. Our method achieved excellent results on the dataset provided by the Traffic4cast Competition 2022, source code is available at https://github.com/OctopusLi/NeurIPS2022-traffic4cast.

Related papers

• BjTT: A Large-scale Multimodal Dataset for Traffic Prediction [49.93028461584377]
  Traditional traffic prediction methods rely on historical traffic data to predict traffic trends. In this work, we explore how generative models combined with text describing the traffic system can be applied for traffic generation. We propose ChatTraffic, the first diffusion model for text-to-traffic generation.
  arXiv  Detail & Related papers  (2024-03-08T04:19:56Z)
• TraffNet: Learning Causality of Traffic Generation for What-if Prediction [4.604622556490027]
  Real-time what-if traffic prediction is crucial for decision making in intelligent traffic management and control. Here, we present a simple deep learning framework called TraffNet that learns the mechanisms of traffic generation for what-if pre-diction.
  arXiv  Detail & Related papers  (2023-03-28T13:12:17Z)
• Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors [25.857884532427292]
  Traffic4cast is a competition series that advances machine learning for modeling complex spatial systems over time. Our dynamic road graph data combine information from road maps, $1012$ probe data points, and stationary vehicle detectors in three cities over the span of two years. In the core challenge, participants are invited to predict the likelihoods of three congestion classes derived from the speed levels in the GPS data for the entire road graph in three cities 15 min into the future. For the extended challenge, participants are tasked to predict the average travel times on super-segments 15 min into the future.
  arXiv  Detail & Related papers  (2023-03-14T10:03:37Z)
• PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Prediction [78.05103666987655]
  spatial-temporal Graph Neural Network (GNN) models have emerged as one of the most promising methods to solve this problem. We propose a novel propagation delay-aware dynamic long-range transFormer, namely PDFormer, for accurate traffic flow prediction. Our method can not only achieve state-of-the-art performance but also exhibit competitive computational efficiency.
  arXiv  Detail & Related papers  (2023-01-19T08:42:40Z)
• Correlating sparse sensing for large-scale traffic speed estimation: A Laplacian-enhanced low-rank tensor kriging approach [76.45949280328838]
  We propose a Laplacian enhanced low-rank tensor (LETC) framework featuring both lowrankness and multi-temporal correlations for large-scale traffic speed kriging. We then design an efficient solution algorithm via several effective numeric techniques to scale up the proposed model to network-wide kriging.
  arXiv  Detail & Related papers  (2022-10-21T07:25:57Z)
• Traffic4cast -- Large-scale Traffic Prediction using 3DResNet and Sparse-UNet [2.568084386350801]
  The aim is to build a machine learning model for predicting the normalized average traffic speed and flow of subregions of multiple-scale cities using historical data points. We explore 3DRparseNetes and Sparse-UNet approaches for the tasks in this competition. Our results show that both of the proposed models achieve much better performance than the baseline algorithms.
  arXiv  Detail & Related papers  (2021-11-10T23:40:52Z)
• Road Network Guided Fine-Grained Urban Traffic Flow Inference [108.64631590347352]
  Accurate inference of fine-grained traffic flow from coarse-grained one is an emerging yet crucial problem. We propose a novel Road-Aware Traffic Flow Magnifier (RATFM) that exploits the prior knowledge of road networks. Our method can generate high-quality fine-grained traffic flow maps.
  arXiv  Detail & Related papers  (2021-09-29T07:51:49Z)
• Feature Engineering for Data-driven Traffic State Forecast in Urban Road Networks [1.370633147306388]
  For longer-term forecasts the traffic state of more distant links or regions of the network are expected to provide valuable information for a data-driven algorithm. This paper studies these expectations of using a clustering network algorithm and one year of Floating Car (FCD) collected by a large fleet of vehicles.
  arXiv  Detail & Related papers  (2020-09-17T15:03:33Z)
• Road Network Metric Learning for Estimated Time of Arrival [93.0759529610483]
  In this paper, we propose the Road Network Metric Learning framework for Estimated Time of Arrival (ETA) It consists of two components: (1) a main regression task to predict the travel time, and (2) an auxiliary metric learning task to improve the quality of link embedding vectors. We show that our method outperforms the state-of-the-art model and the promotion concentrates on the cold links with few data.
  arXiv  Detail & Related papers  (2020-06-24T04:45:14Z)
• Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting [88.5550074808201]
  We propose Geographic and Long term Temporal Graph Convolutional Recurrent Neural Network (GLT-GCRNN) for traffic forecasting. In this work, we propose a novel framework for traffic forecasting that learns the rich interactions between roads sharing similar geographic or longterm temporal patterns.
  arXiv  Detail & Related papers  (2020-04-23T03:50:46Z)
• PCNN: Deep Convolutional Networks for Short-term Traffic Congestion Prediction [16.010576606023417]
  We propose a novel method named PCNN based on deep Convolutional Neural Network, modeling Periodic traffic data for short-term traffic congestion prediction. PCNN has two pivotal procedures: time series folding and multi-grained learning. Experimental results on a real-world urban traffic dataset confirm that folding time series data into a two-dimensional matrix is effective.
  arXiv  Detail & Related papers  (2020-03-16T05:36:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.