mlsanityData to 14 Oct 2026

From Optimization to Prediction: Transformer-Based Path-Flow Estimation to the Traffic Assignment Problem

arXiv 2510.19889 ↗First posted 22 Oct 2025cs.LG cs.AI math.OCcited by 1

Not on the map. Why?

Abstract (arXiv)

The traffic assignment problem is essential for traffic flow analysis, traditionally solved using mathematical programs under the Equilibrium principle. These methods become computationally prohibitive for large-scale networks due to non-linear growth in complexity with the number of OD pairs. This study introduces a novel data-driven approach using deep neural networks, specifically leveraging the Transformer architecture, to predict equilibrium path flows directly. By focusing on path-level traffic distribution, the proposed model captures intricate correlations between OD pairs, offering a more detailed and flexible analysis compared to traditional link-level approaches. The Transformer-based model drastically reduces computation time, while adapting to changes in demand and network structure without the need for recalculation. Numerical experiments are conducted on the Manhattan-like synthetic network, the Sioux Falls network, and the Eastern-Massachusetts network. The results demonstrate that the proposed model is orders of magnitude faster than conventional optimization. It efficiently estimates path-level traffic flows in multi-class networks, reducing computational costs and improving prediction accuracy by capturing detailed trip and flow information. The model also adapts flexibly to varying demand and network conditions, supporting traffic management and enabling rapid `what-if' analyses for enhanced transportation planning and policy-making.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 16 of its 57 references that are in the map. First posted on arXiv 22 Oct 2025.

Builds on

16 of 57 references.

References · 16

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Inductive Representation Learning on Large Graphscited by 6,320
  5. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  6. 2017Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecastingcited by 1,136
  7. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  8. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  9. 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 172
  10. 2017Deep Forecast: Deep Learning-based Spatio-Temporal Forecastingcited by 13
  11. 2023End-to-End Heterogeneous Graph Neural Networks for Traffic Assignmentcited by 13
  12. 2022Data-Driven Traffic Assignment: A Novel Approach for Learning Traffic Flow Patterns Using a Graph Convolutional Neural Networkcited by 12
4 more
  1. 2025Multi-Class Traffic Assignment using Multi-View Heterogeneous Graph Attention Networkscited by 4
  2. 2022Network Level Spatial Temporal Traffic State Forecasting with Hierarchical-Attention-LSTM (HierAttnLSTM)cited by 2
  3. 2024A Structure-Aware Lane Graph Transformer Model for Vehicle Trajectory Predictioncited by 2
  4. 2021A Distributed Gradient Approach for System Optimal Dynamic Traffic Assignmentcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026GUIDED Network-Agnostic Feature Initialization for Spatial Transferability in GNN-based Modelscited by 0