Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
162 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Learning Heuristics for Transit Network Design and Improvement with Deep Reinforcement Learning (2404.05894v5)

Published 8 Apr 2024 in cs.LG, cs.AI, and cs.NE

Abstract: Planning a network of public transit routes is a challenging optimization problem. Metaheuristic algorithms search through the space of possible transit networks by applying heuristics that randomly alter routes in a network. The design of these heuristics has a major impact on the quality of the result. In this paper, we use deep reinforcement learning to train a graph neural net to provide heuristics for an evolutionary algorithm. These neural heuristics improve the algorithm's results on benchmark synthetic cities with 70 nodes or more, and achieve new state-of-the-art results on the challenging Mumford benchmark. They also improve upon a simulation of the real transit network in the city of Laval, Canada, by 52% and 25% on two key metrics, and offer cost savings of up to 19% over the city's existing transit network.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (68)
  1. Agence métropolitaine de transport, “Enquête origine-destination 2013,” 2013, montreal, QC.
  2. L. Ahmed, C. Mumford, and A. Kheiri, “Solving urban transit route design problem using selection hyper-heuristics,” European Journal of Operational Research, vol. 274, no. 2, pp. 545–559, 2019.
  3. G. Ai, X. Zuo, G. Chen, and B. Wu, “Deep reinforcement learning based dynamic optimization of bus timetable,” Applied Soft Computing, vol. 131, p. 109752, 2022.
  4. D. Applegate, R. E. Bixby, V. Chvátal, and W. J. Cook, “Concorde tsp solver,” 2001. [Online]. Available: https://www.math.uwaterloo.ca/tsp/concorde/index.html
  5. P. W. Battaglia, J. B. Hamrick, V. Bapst, A. Sanchez-Gonzalez, V. Zambaldi, M. Malinowski, A. Tacchetti, D. Raposo, A. Santoro, R. Faulkner et al., “Relational inductive biases, deep learning, and graph networks,” arXiv preprint arXiv:1806.01261, 2018.
  6. Y. Bengio, A. Lodi, and A. Prouvost, “Machine learning for combinatorial optimization: a methodological tour d’horizon,” European Journal of Operational Research, vol. 290, no. 2, pp. 405–421, 2021.
  7. S. Brody, U. Alon, and E. Yahav, “How attentive are graph attention networks?” 2021. [Online]. Available: https://arxiv.org/abs/2105.14491
  8. J. Bruna, W. Zaremba, A. Szlam, and Y. LeCun, “Spectral networks and locally connected networks on graphs,” arXiv preprint arXiv:1312.6203, 2013.
  9. X. Chen and Y. Tian, “Learning to perform local rewriting for combinatorial optimization,” Advances in Neural Information Processing Systems, vol. 32, 2019.
  10. S. I.-J. Chien, Y. Ding, and C. Wei, “Dynamic bus arrival time prediction with artificial neural networks,” Journal of transportation engineering, vol. 128, no. 5, pp. 429–438, 2002.
  11. J. Choo, Y.-D. Kwon, J. Kim, J. Jae, A. Hottung, K. Tierney, and Y. Gwon, “Simulation-guided beam search for neural combinatorial optimization,” Advances in Neural Information Processing Systems, vol. 35, pp. 8760–8772, 2022.
  12. P. R. d O Costa, J. Rhuggenaath, Y. Zhang, and A. Akcay, “Learning 2-opt heuristics for the traveling salesman problem via deep reinforcement learning,” in Asian conference on machine learning.   PMLR, 2020, pp. 465–480.
  13. H. Dai, E. B. Khalil, Y. Zhang, B. Dilkina, and L. Song, “Learning combinatorial optimization algorithms over graphs,” arXiv preprint arXiv:1704.01665, 2017.
  14. A. Darwish, M. Khalil, and K. Badawi, “Optimising public bus transit networks using deep reinforcement learning,” in 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC).   IEEE, 2020, pp. 1–7.
  15. M. Defferrard, X. Bresson, and P. Vandergheynst, “Convolutional neural networks on graphs with fast localized spectral filtering,” CoRR, vol. abs/1606.09375, 2016. [Online]. Available: http://arxiv.org/abs/1606.09375
  16. J. Durán-Micco and P. Vansteenwegen, “A survey on the transit network design and frequency setting problem,” Public Transport, vol. 14, no. 1, pp. 155–190, 2022.
  17. D. K. Duvenaud, D. Maclaurin, J. Iparraguirre, R. Bombarell, T. Hirzel, A. Aspuru-Guzik, and R. P. Adams, “Convolutional networks on graphs for learning molecular fingerprints,” Advances in neural information processing systems, vol. 28, 2015.
  18. S. Fortune, “Voronoi diagrams and delaunay triangulations,” Computing in Euclidean geometry, pp. 225–265, 1995.
  19. Z.-H. Fu, K.-B. Qiu, and H. Zha, “Generalize a small pre-trained model to arbitrarily large tsp instances,” in Proceedings of the AAAI conference on artificial intelligence, vol. 35, no. 8, 2021, pp. 7474–7482.
  20. J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, and G. E. Dahl, “Neural message passing for quantum chemistry,” in Proceedings of the 34th International Conference on Machine Learning, ser. Proceedings of Machine Learning Research, D. Precup and Y. W. Teh, Eds., vol. 70.   PMLR, 06–11 Aug 2017, pp. 1263–1272. [Online]. Available: https://proceedings.mlr.press/v70/gilmer17a.html
  21. J. Guan, H. Yang, and S. Wirasinghe, “Simultaneous optimization of transit line configuration and passenger line assignment,” Transportation Research Part B: Methodological, vol. 40, pp. 885–902, 12 2006.
  22. V. Guihaire and J.-K. Hao, “Transit network design and scheduling: A global review,” Transportation Research Part A: Policy and Practice, vol. 42, no. 10, pp. 1251–1273, 2008.
  23. A. Holliday and G. Dudek, “Augmenting transit network design algorithms with deep learning,” in 2023 26th IEEE International Conference on Intelligent Transportation Systems (ITSC).   IEEE, 2023.
  24. ——, “A neural-evolutionary algorithm for autonomous transit network design,” in presented at 2024 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2024.
  25. A. Hottung and K. Tierney, “Neural large neighborhood search for the capacitated vehicle routing problem,” arXiv preprint arXiv:1911.09539, 2019.
  26. G. Hüsselmann, J. H. van Vuuren, and S. J. Andersen, “An improved solution methodology for the urban transit routing problem,” Computers & Operations Research, p. 106481, 2023.
  27. K. A. Islam, I. M. Moosa, J. Mobin, M. A. Nayeem, and M. S. Rahman, “A heuristic aided stochastic beam search algorithm for solving the transit network design problem,” Swarm and Evolutionary Computation, vol. 46, pp. 154–170, 2019.
  28. R. Jeong and R. Rilett, “Bus arrival time prediction using artificial neural network model,” in Proceedings. The 7th international IEEE conference on intelligent transportation systems (IEEE Cat. No. 04TH8749).   IEEE, 2004, pp. 988–993.
  29. Z. Jiang, W. Fan, W. Liu, B. Zhu, and J. Gu, “Reinforcement learning approach for coordinated passenger inflow control of urban rail transit in peak hours,” Transportation Research Part C: Emerging Technologies, vol. 88, pp. 1–16, 2018. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0968090X18300111
  30. M. P. John, C. L. Mumford, and R. Lewis, “An improved multi-objective algorithm for the urban transit routing problem,” in Evolutionary Computation in Combinatorial Optimisation, C. Blum and G. Ochoa, Eds.   Berlin, Heidelberg: Springer Berlin Heidelberg, 2014, pp. 49–60.
  31. A. Kar, A. L. Carrel, H. J. Miller, and H. T. Le, “Public transit cuts during covid-19 compound social vulnerability in 22 us cities,” Transportation Research Part D: Transport and Environment, vol. 110, p. 103435, 2022.
  32. K. Kepaptsoglou and M. Karlaftis, “Transit route network design problem: Review,” Journal of Transportation Engineering, vol. 135, no. 8, pp. 491–505, 2009.
  33. M. Kim, J. Park et al., “Learning collaborative policies to solve np-hard routing problems,” Advances in Neural Information Processing Systems, vol. 34, pp. 10 418–10 430, 2021.
  34. D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization,” in ICLR, 2015.
  35. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907, 2016.
  36. W. Kool, H. V. Hoof, and M. Welling, “Attention, learn to solve routing problems!” in ICLR, 2019.
  37. F. Kılıç and M. Gök, “A demand based route generation algorithm for public transit network design,” Computers & Operations Research, vol. 51, pp. 21–29, 2014. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0305054814001300
  38. C. Li, L. Bai, W. Liu, L. Yao, and S. T. Waller, “Graph neural network for robust public transit demand prediction,” IEEE Transactions on Intelligent Transportation Systems, 2020.
  39. H. Lin and C. Tang, “Analysis and optimization of urban public transport lines based on multiobjective adaptive particle swarm optimization,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 9, pp. 16 786–16 798, 2022.
  40. L. Liu, H. J. Miller, and J. Scheff, “The impacts of covid-19 pandemic on public transit demand in the united states,” Plos one, vol. 15, no. 11, p. e0242476, 2020.
  41. Y. Ma, J. Li, Z. Cao, W. Song, L. Zhang, Z. Chen, and J. Tang, “Learning to iteratively solve routing problems with dual-aspect collaborative transformer,” Advances in Neural Information Processing Systems, vol. 34, pp. 11 096–11 107, 2021.
  42. C. E. Mandl, “Evaluation and optimization of urban public transportation networks,” European Journal of Operational Research, vol. 5, no. 6, pp. 396–404, 1980.
  43. A. Mirhoseini, A. Goldie, M. Yazgan, J. W. Jiang, E. Songhori, S. Wang, Y.-J. Lee, E. Johnson, O. Pathak, A. Nazi et al., “A graph placement methodology for fast chip design,” Nature, vol. 594, no. 7862, pp. 207–212, 2021.
  44. C. L. Mumford, “Supplementary material for: New heuristic and evolutionary operators for the multi-objective urban transit routing problem, cec 2013,” https://users.cs.cf.ac.uk/C.L.Mumford/Research%20Topics/UTRP/CEC2013Supp.zip, 2013, accessed: 2023-03-24.
  45. ——, “New heuristic and evolutionary operators for the multi-objective urban transit routing problem,” in 2013 IEEE congress on evolutionary computation.   IEEE, 2013, pp. 939–946.
  46. T. N. Mundhenk, M. Landajuela, R. Glatt, C. P. Santiago, D. M. Faissol, and B. K. Petersen, “Symbolic regression via neural-guided genetic programming population seeding,” arXiv preprint arXiv:2111.00053, 2021.
  47. M. Nikolić and D. Teodorović, “Transit network design by bee colony optimization,” Expert Systems with Applications, vol. 40, no. 15, pp. 5945–5955, 2013.
  48. C. Quak, “Bus line planning,” A passenger-oriented approach of the construction of a global line network and an efficient timetable. Master’s thesis, Delft University, Delft, Netherlands, 2003.
  49. J.-P. Rodrigue, “Parallel modelling and neural networks: An overview for transportation/land use systems,” Transportation Research Part C: Emerging Technologies, vol. 5, no. 5, pp. 259–271, 1997. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0968090X97000144
  50. K. Sörensen, “Metaheuristics—the metaphor exposed,” International Transactions in Operational Research, vol. 22, no. 1, pp. 3–18, 2015.
  51. K. Sörensen, M. Sevaux, and F. Glover, “A history of metaheuristics,” in Handbook of heuristics.   Springer, 2018, pp. 791–808.
  52. Statistics Canada, “Census profile, 2021 census of population,” 2023, accessed: 2023-10-25. [Online]. Available: https://www12.statcan.gc.ca/census-recensement/2021/dp-pd/prof/details/page.cfm
  53. ——, “Census dissemination area boundary files,” 2021, accessed: 2023-07-01. [Online]. Available: https://www150.statcan.gc.ca/n1/en/catalogue/92-169-X
  54. STL, “Stl gtfs,” retreived 2020. [Online]. Available: https://transitfeeds.com/p/societe-de-transport-de-laval/38/1383528159
  55. Q. Sykora, M. Ren, and R. Urtasun, “Multi-agent routing value iteration network,” in International Conference on Machine Learning.   PMLR, 2020, pp. 9300–9310.
  56. R. van Nes, “Multiuser-class urban transit network design,” Transportation Research Record, vol. 1835, no. 1, pp. 25–33, 2003. [Online]. Available: https://doi.org/10.3141/1835-04
  57. A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” in Advances in neural information processing systems, 2017, pp. 5998–6008.
  58. O. Vinyals, M. Fortunato, and N. Jaitly, “Pointer networks,” arXiv preprint arXiv:1506.03134, 2015.
  59. T. Wang, Z. Zhu, J. Zhang, J. Tian, and W. Zhang, “A large-scale traffic signal control algorithm based on multi-layer graph deep reinforcement learning,” Transportation Research Part C: Emerging Technologies, vol. 162, p. 104582, 2024. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0968090X24001037
  60. R. J. Williams, “Simple statistical gradient-following algorithms for connectionist reinforcement learning,” Machine learning, vol. 8, no. 3, pp. 229–256, 1992.
  61. Y. Wu, W. Song, Z. Cao, J. Zhang, and A. Lim, “Learning improvement heuristics for solving routing problems,” IEEE transactions on neural networks and learning systems, vol. 33, no. 9, pp. 5057–5069, 2021.
  62. Y. Xiong and J. B. Schneider, “Transportation network design using a cumulative genetic algorithm and neural network,” Transportation Research Record, vol. 1364, 1992.
  63. H. Yan, Z. Cui, X. Chen, and X. Ma, “Distributed multiagent deep reinforcement learning for multiline dynamic bus timetable optimization,” IEEE Transactions on Industrial Informatics, vol. 19, pp. 469–479, 2023.
  64. J. Yang and Y. Jiang, “Application of modified nsga-ii to the transit network design problem,” Journal of Advanced Transportation, vol. 2020, pp. 1–24, 2020.
  65. R. Ying, R. He, K. Chen, P. Eksombatchai, W. L. Hamilton, and J. Leskovec, “Graph convolutional neural networks for web-scale recommender systems,” CoRR, vol. abs/1806.01973, 2018. [Online]. Available: http://arxiv.org/abs/1806.01973
  66. S. Yoo, J. B. Lee, and H. Han, “A reinforcement learning approach for bus network design and frequency setting optimisation,” Public Transport, pp. 1–32, 2023.
  67. L. Zou, J.-m. Xu, and L.-x. Zhu, “Light rail intelligent dispatching system based on reinforcement learning,” in 2006 International Conference on Machine Learning and Cybernetics, 2006, pp. 2493–2496.
  68. M. Y. Çodur and A. Tortum, “An artificial intelligent approach to traffic accident estimation: Model development and application,” Transport, vol. 24, no. 2, pp. 135–142, 2009.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets