mlsanityData to 14 Oct 2026

Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis

arXiv 2311.00164 ↗First posted 31 Oct 2023cs.SI cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

We consider the problem of traffic accident analysis on a road network based on road network connections and traffic volume. Previous works have designed various deep-learning methods using historical records to predict traffic accident occurrences. However, there is a lack of consensus on how accurate existing methods are, and a fundamental issue is the lack of public accident datasets for comprehensive evaluations. This paper constructs a large-scale, unified dataset of traffic accident records from official reports of various states in the US, totaling 9 million records, accompanied by road networks and traffic volume reports. Using this new dataset, we evaluate existing deep-learning methods for predicting the occurrence of accidents on road networks. Our main finding is that graph neural networks such as GraphSAGE can accurately predict the number of accidents on roads with less than 22% mean absolute error (relative to the actual count) and whether an accident will occur or not with over 87% AUROC, averaged over states. We achieve these results by using multitask learning to account for cross-state variabilities (e.g., availability of accident labels) and transfer learning to combine traffic volume with accident prediction. Ablation studies highlight the importance of road graph-structural features, amongst other features. Lastly, we discuss the implications of the analysis and develop a package for easily using our new dataset.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 47 of its 75 references that are in the map. First posted on arXiv 31 Oct 2023.

Builds on

47 of 75 references.

References · 47

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2018How Powerful are Graph Neural Networks?cited by 4,393
  4. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  5. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  6. 2014DeepWalk: Online Learning of Social Representationscited by 1,547
  7. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  8. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  9. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  10. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 829
  11. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  12. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
35 more
  1. 2020Adaptive Graph Convolutional Recurrent Network for Traffic Forecastingcited by 530
  2. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  3. 2019Which Tasks Should Be Learned Together in Multi-task Learning?cited by 375
  4. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 329
  5. 2021Spectral Temporal Graph Neural Network for Multivariate Time-series Forecastingcited by 299
  6. 2021Graph Contrastive Learning Automatedcited by 287
  7. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 261
  8. 2019Evaluating Protein Transfer Learning with TAPEcited by 231
  9. 2021Efficiently Identifying Task Groupings for Multi-Task Learningcited by 222
  10. 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 172
  11. 2020Understanding and Improving Information Transfer in Multi-Task Learningcited by 114
  12. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  13. 2016OSMnx: New Methods for Acquiring, Constructing, Analyzing, and Visualizing Complex Street Networkscited by 110
  14. 2020Transfer Learning of Graph Neural Networks with Ego-graph Information Maximizationcited by 93
  15. 2022BOND: Benchmarking Unsupervised Outlier Node Detection on Static Attributed Graphscited by 80
  16. 2020ATOM3D: Tasks On Molecules in Three Dimensionscited by 74
  17. 2019Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Predictioncited by 64
  18. 2022DGraph: A Large-Scale Financial Dataset for Graph Anomaly Detectioncited by 63
  19. 2022A Comprehensive Study on Large-Scale Graph Training: Benchmarking and Rethinkingcited by 56
  20. 2020A Large-Scale Database for Graph Representation Learningcited by 55
  21. 2021Improved Regularization and Robustness for Fine-tuning in Neural Networkscited by 45
  22. 2019Predicting Citywide Crowd Flows in Irregular Regions Using Multi-View Graph Convolutional Networkscited by 40
  23. 2023Generalization in Graph Neural Networks: Improved PAC-Bayesian Bounds on Graph Diffusioncited by 40
  24. 2022Spatial-Temporal Hypergraph Self-Supervised Learning for Crime Predictioncited by 39
  25. 2022Robust Fine-Tuning of Deep Neural Networks with Hessian-based Generalization Guaranteescited by 34
  26. 2020RiskOracle: A Minute-level Citywide Traffic Accident Forecasting Frameworkcited by 33
  27. 2022Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networkscited by 29
  28. 2020Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transferscited by 27
  29. 2019Accident Risk Prediction based on Heterogeneous Sparse Data: New Dataset and Insightscited by 24
  30. 2023Automated Spatio-Temporal Graph Contrastive Learningcited by 24
  31. 2023Identification of Negative Transfers in Multitask Learning Using Surrogate Modelscited by 20
  32. 2023Boosting Multitask Learning on Graphs through Higher-Order Task Affinitiescited by 15
  33. 2017Real-time Traffic Accident Risk Prediction based on Frequent Pattern Treecited by 12
  34. 2019RoadTagger: Robust Road Attribute Inference with Graph Neural Networkscited by 11
  35. 2023TAP: A Comprehensive Data Repository for Traffic Accident Prediction in Road Networkscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 8; 2026: 2.

13 papers.

Sort:

By area:

  1. 2024Scalable Multitask Learning Using Gradient-based Estimation of Task Affinitycited by 20
  2. 2025Simulating the Unseen: Crash Prediction Must Learn from What Did Not Happencited by 5
  3. 2024Recent Advances in Traffic Accident Analysis and Prediction: A Comprehensive Review of Machine Learning Techniquescited by 4
  4. 2025Digital Twin-Driven Pavement Health Monitoring and Maintenance Optimization Using Graph Neural Networkscited by 2
  5. 2024Learning Tree-Structured Composition of Data Augmentationcited by 1
  6. 2025Multimodal Large Language Models for Enhanced Traffic Safety: A Comprehensive Review and Future Trendscited by 1
  7. 2025Privacy Risk Predictions Based on Fundamental Understanding of Personal Data and an Evolving Threat Landscapecited by 1
  8. 2025STARN-GAT: A Multi-Modal Spatio-Temporal Graph Attention Network for Accident Severity Predictioncited by 0
  9. 2025MSGAT-GRU: A Multi-Scale Graph Attention and Recurrent Model for Spatiotemporal Road Accident Predictioncited by 0
  10. 2025Metropolis-Scale Road Network Datasets for Fine-Grained Urban Traffic Modelingcited by 0
  11. 2025Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimationcited by 0
  12. 2026hia-gat: A Heterogeneous Interaction-Aware Graph Attention Network For Frame-Level Traffic Conflict Risk Prediction On Freewayscited by 0
1 more
  1. 2026Replication Failure and Trivial Baselines in Road-Level Crash Predictioncited by 0