Traffic4cast 2020 -- Graph Ensemble Net and the Importance of Feature And Loss Function Design for Traffic Prediction

• URL: http://arxiv.org/abs/2012.02115v1
• Date: Thu, 3 Dec 2020 17:49:04 GMT
• Title: Traffic4cast 2020 -- Graph Ensemble Net and the Importance of Feature And Loss Function Design for Traffic Prediction
• Authors: Qi Qi, Pak Hay Kwok
• Abstract summary: Similar to Traffic4cast 2019, Traffic4cast 2020 challenged its contestants to develop algorithms that can predict the future traffic states of big cities. We studied the importance of feature and loss function design, and achieved significant improvement to the best performing U-Net solution from last year. Our final solution, an ensemble of our U-Net and GNN, achieved the 4th place solution in Traffic4cast 2020.
• Score: 4.0847949901305
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper details our solution to Traffic4cast 2020. Similar to Traffic4cast 2019, Traffic4cast 2020 challenged its contestants to develop algorithms that can predict the future traffic states of big cities. Our team tackled this challenge on two fronts. We studied the importance of feature and loss function design, and achieved significant improvement to the best performing U-Net solution from last year. We also explored the use of Graph Neural Networks and introduced a novel ensemble GNN architecture which outperformed the GNN solution from last year. While our GNN was improved, it was still unable to match the performance of U-Nets and the potential reasons for this shortfall were discussed. Our final solution, an ensemble of our U-Net and GNN, achieved the 4th place solution in Traffic4cast 2020.

Related papers

• A Survey of Graph Neural Networks in Real world: Imbalance, Noise, Privacy and OOD Challenges [75.37448213291668]
  This paper systematically reviews existing Graph Neural Networks (GNNs) We first highlight the four key challenges faced by existing GNNs, paving the way for our exploration of real-world GNN models.
  arXiv  Detail & Related papers  (2024-03-07T13:10:37Z)
• A Survey on Graph Neural Networks in Intelligent Transportation Systems [11.863528235605457]
  Graph Neural Networks (GNNs) have emerged as a highly competitive method in the ITS field since 2019. This paper aims to review the applications of GNNs in six representative and emerging ITS domains: traffic forecasting, autonomous vehicles, traffic signal control, transportation safety, demand prediction, and parking management.
  arXiv  Detail & Related papers  (2024-01-01T09:53:24Z)
• LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagation [51.552170474958736]
  We propose to capture long-distance dependency in graphs by shallower models instead of deeper models, which leads to a much more efficient model, LazyGNN, for graph representation learning. LazyGNN is compatible with existing scalable approaches (such as sampling methods) for further accelerations through the development of mini-batch LazyGNN. Comprehensive experiments demonstrate its superior prediction performance and scalability on large-scale benchmarks.
  arXiv  Detail & Related papers  (2023-02-03T02:33:07Z)
• QT-Routenet: Improved GNN generalization to larger 5G networks by fine-tuning predictions from queueing theory [2.4366811507669124]
  We tackle the problem of generalization when applying a model to a 5G network. We propose to first extract robust features related to Queueing Theory (QT) We then fine-tune the analytical baseline prediction using a modification of the Routenet Graph Neural Network (GNN) model.
  arXiv  Detail & Related papers  (2022-07-13T16:49:37Z)
• Trustworthy Graph Neural Networks: Aspects, Methods and Trends [115.84291569988748]
  Graph neural networks (GNNs) have emerged as competent graph learning methods for diverse real-world scenarios. Performance-oriented GNNs have exhibited potential adverse effects like vulnerability to adversarial attacks. To avoid these unintentional harms, it is necessary to build competent GNNs characterised by trustworthiness.
  arXiv  Detail & Related papers  (2022-05-16T02:21:09Z)
• Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020 [61.31176652211479]
  Graph Neural Networks (GNNs) have been proven to be effective in modeling graph structured data and many variants of GNN architectures have been proposed. Researchers naturally adopt Automated Machine Learning on Graph Learning, aiming to reduce the human effort and achieve generally top-performing GNNs. To understand GNN practitioners' automated solutions, we organized AutoGraph Challenge at KDD Cup 2020, emphasizing on automated graph neural networks for node classification.
  arXiv  Detail & Related papers  (2022-04-06T07:06:48Z)
• Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes [61.16854022482186]
  The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future. U-Nets proved to be the winning architecture, demonstrating an ability to extract relevant features in this complex real-world geo-spatial process. The competition now covers ten cities over 2 years, providing data compiled from over 1012 GPS probe data.
  arXiv  Detail & Related papers  (2022-03-31T14:40:01Z)
• LHNN: Lattice Hypergraph Neural Network for VLSI Congestion Prediction [70.31656245793302]
  lattice hypergraph (LH-graph) is a novel graph formulation for circuits. LHNN constantly achieves more than 35% improvements compared with U-nets and Pix2Pix on the F1 score.
  arXiv  Detail & Related papers  (2022-03-24T03:31:18Z)
• Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation [0.0]
  We present our solution to the Traffic4Cast 2021 Core Challenge. The challenge focuses on the temporal domain shift in traffic due to the COVID-19 pandemic. Our solution has ranked third in the final competition.
  arXiv  Detail & Related papers  (2021-11-05T11:49:52Z)
• TLab: Traffic Map Movie Forecasting Based on HR-NET [23.40323690536007]
  In our solution, hand-crafted features are input into the model in a form of channels. In terms of prediction accuracy, our solution has won 2nd place in NeurIPS 2020, Traffic4cast Challenge.
  arXiv  Detail & Related papers  (2020-11-13T18:48:13Z)

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.