Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Towards Omni-generalizable Neural Methods for Vehicle Routing Problems (2305.19587v2)

Published 31 May 2023 in cs.LG and cs.AI

Abstract: Learning heuristics for vehicle routing problems (VRPs) has gained much attention due to the less reliance on hand-crafted rules. However, existing methods are typically trained and tested on the same task with a fixed size and distribution (of nodes), and hence suffer from limited generalization performance. This paper studies a challenging yet realistic setting, which considers generalization across both size and distribution in VRPs. We propose a generic meta-learning framework, which enables effective training of an initialized model with the capability of fast adaptation to new tasks during inference. We further develop a simple yet efficient approximation method to reduce the training overhead. Extensive experiments on both synthetic and benchmark instances of the traveling salesman problem (TSP) and capacitated vehicle routing problem (CVRP) demonstrate the effectiveness of our method. The code is available at: https://github.com/RoyalSkye/Omni-VRP.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (75)
  1. Learning what to defer for maximum independent sets. In ICML, pp.  134–144. PMLR, 2020.
  2. Augerat, P. Approche polyèdrale du problème de tournées de véhicules. PhD thesis, Institut National Polytechnique de Grenoble-INPG, 1995.
  3. Rezero is all you need: Fast convergence at large depth. In UAI, pp.  1352–1361. PMLR, 2021.
  4. Attention, filling in the gaps for generalization in routing problems. In ECMLPKDD, 2022.
  5. Neural combinatorial optimization with reinforcement learning. In ICLR Workshop Track, 2017.
  6. Curriculum learning. In ICML, pp.  41–48, 2009.
  7. Machine learning for combinatorial optimization: a methodological tour d’horizon. European Journal of Operational Research, 290(2):405–421, 2021.
  8. Learning generalizable models for vehicle routing problems via knowledge distillation. In NeurIPS, 2022.
  9. Evolving diverse tsp instances by means of novel and creative mutation operators. In Proceedings of the 15th ACM/SIGEVO Conference on Foundations of Genetic Algorithms, pp.  58–71, 2019.
  10. Residual gated graph convnets. arXiv preprint arXiv:1711.07553, 2017.
  11. Vehicle routing problems for city logistics. EURO Journal on Transportation and Logistics, 6(1):51–79, 2017.
  12. Learning to perform local rewriting for combinatorial optimization. In NeurIPS, volume 32, 2019.
  13. Croes, G. A. A method for solving traveling-salesman problems. Operations research, 6(6):791–812, 1958.
  14. Learning 2-opt heuristics for the traveling salesman problem via deep reinforcement learning. In Asian Conference on Machine Learning, pp.  465–480. PMLR, 2020.
  15. Learning combinatorial optimization algorithms over graphs. In NeurIPS, volume 30, 2017.
  16. Bq-nco: Bisimulation quotienting for generalizable neural combinatorial optimization. arXiv preprint arXiv:2301.03313, 2023.
  17. Model-agnostic meta-learning for fast adaptation of deep networks. In ICML, pp.  1126–1135. PMLR, 2017.
  18. Bootstrapped meta-learning. In ICLR, 2022.
  19. Generalize a small pre-trained model to arbitrarily large tsp instances. In AAAI, volume 35, pp.  7474–7482, 2021.
  20. Vehicle routing problems with alternative paths: An application to on-demand transportation. European Journal of Operational Research, 204(1):62–75, 2010.
  21. Generalization of neural combinatorial solvers through the lens of adversarial robustness. In ICLR, 2022.
  22. Helsgaun, K. An effective implementation of the lin–kernighan traveling salesman heuristic. European journal of operational research, 126(1):106–130, 2000.
  23. Helsgaun, K. An extension of the lin-kernighan-helsgaun tsp solver for constrained traveling salesman and vehicle routing problems. Roskilde: Roskilde University, pp.  24–50, 2017.
  24. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015.
  25. Meta-learning in neural networks: A survey. IEEE transactions on pattern analysis and machine intelligence, 2021.
  26. Neural large neighborhood search for the capacitated vehicle routing problem. In European Conference on Artificial Intelligence, pp. 443–450. IOS Press, 2020.
  27. Efficient active search for combinatorial optimization problems. In ICLR, 2022.
  28. Generalize learned heuristics to solve large-scale vehicle routing problems in real-time. In ICLR, 2023.
  29. Graph neural network guided local search for the traveling salesperson problem. In ICLR, 2022.
  30. Learning to solve routing problems via distributionally robust optimization. In AAAI, 2022.
  31. An efficient graph convolutional network technique for the travelling salesman problem. arXiv preprint arXiv:1906.01227, 2019.
  32. Learning tsp requires rethinking generalization. In International Conference on Principles and Practice of Constraint Programming, 2021.
  33. Learning collaborative policies to solve np-hard routing problems. In NeurIPS, volume 34, pp.  10418–10430, 2021.
  34. Sym-NCO: Leveraging symmetricity for neural combinatorial optimization. In NeurIPS, 2022a.
  35. Scale-conditioned adaptation for large scale combinatorial optimization. In NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications, 2022b.
  36. Adam: A method for stochastic optimization. In ICLR, 2015.
  37. Vehicle routing problem and related algorithms for logistics distribution: A literature review and classification. Operational research, pp.  1–30, 2022.
  38. Attention, learn to solve routing problems! In ICLR, 2018.
  39. Pomo: Policy optimization with multiple optima for reinforcement learning. In NeurIPS, volume 33, pp.  21188–21198, 2020.
  40. Matrix encoding networks for neural combinatorial optimization. In NeurIPS, volume 34, pp.  5138–5149, 2021.
  41. Learning to delegate for large-scale vehicle routing. In NeurIPS, volume 34, pp.  26198–26211, 2021.
  42. Evaluating curriculum learning strategies in neural combinatorial optimization. In NeurIPS 2020 Workshop on Learning Meets Combinatorial Algorithms, 2020.
  43. How good is neural combinatorial optimization? arXiv preprint arXiv:2209.10913, 2022.
  44. A learning-based iterative method for solving vehicle routing problems. In ICLR, 2020.
  45. Combinatorial optimization by graph pointer networks and hierarchical reinforcement learning. arXiv preprint arXiv:1911.04936, 2019.
  46. Learning to iteratively solve routing problems with dual-aspect collaborative transformer. In NeurIPS, volume 34, pp.  11096–11107, 2021.
  47. On the generalization of neural combinatorial optimization heuristics. In ECMLPKDD, 2022.
  48. Reinforcement learning for solving the vehicle routing problem. In NeurIPS, volume 31, 2018.
  49. On first-order meta-learning algorithms. arXiv preprint arXiv:1803.02999, 2018.
  50. DIMES: A differentiable meta solver for combinatorial optimization problems. In NeurIPS, 2022.
  51. 10,000 optimal cvrp solutions for testing machine learning based heuristics. In AAAI Workshop on Machine Learning for Operations Research (ML4OR), 2022.
  52. Rapid learning or feature reuse? towards understanding the effectiveness of maml. In ICLR, 2020.
  53. Reinelt, G. Tsplib—a traveling salesman problem library. ORSA journal on computing, 3(4):376–384, 1991.
  54. Distributionally robust neural networks for group shifts: On the importance of regularization for worst-case generalization. In ICLR, 2020.
  55. Learning a sat solver from single-bit supervision. In ICLR, 2019.
  56. Shaw, P. Using constraint programming and local search methods to solve vehicle routing problems. In International conference on principles and practice of constraint programming, pp.  417–431. Springer, 1998.
  57. Understanding tsp difficulty by learning from evolved instances. In International conference on learning and intelligent optimization, pp.  266–280. Springer, 2010.
  58. Difusco: Graph-based diffusion solvers for combinatorial optimization. arXiv preprint arXiv:2302.08224, 2023.
  59. New benchmark instances for the capacitated vehicle routing problem. European Journal of Operational Research, 257(3):845–858, 2017.
  60. Attention is all you need. In NeurIPS, volume 30, 2017.
  61. Vidal, T. Hybrid genetic search for the cvrp: Open-source implementation and swap* neighborhood. Computers & Operations Research, 140:105643, 2022.
  62. A perspective view and survey of meta-learning. Artificial intelligence review, 18(2):77–95, 2002.
  63. Pointer networks. In NeurIPS, volume 28, 2015.
  64. A game-theoretic approach for improving generalization ability of tsp solvers. In ICLR 2022 Workshop on Gamification and Multiagent Solutions, 2022.
  65. A bi-level framework for learning to solve combinatorial optimization on graphs. In NeurIPS, volume 34, pp.  21453–21466, 2021.
  66. Williams, R. J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8(3):229–256, 1992.
  67. No free lunch theorems for optimization. IEEE transactions on evolutionary computation, 1(1):67–82, 1997.
  68. Learning improvement heuristics for solving routing problems. IEEE transactions on neural networks and learning systems, 2021.
  69. Neural airport ground handling. IEEE Transactions on Intelligent Transportation Systems, 2023.
  70. Multi-decoder attention model with embedding glimpse for solving vehicle routing problems. In AAAI, volume 35, pp.  12042–12049, 2021a.
  71. Neurolkh: Combining deep learning model with lin-kernighan-helsgaun heuristic for solving the traveling salesman problem. In NeurIPS, volume 34, pp.  7472–7483, 2021b.
  72. It’s not what machines can learn, it’s what we cannot teach. In ICML, pp.  10831–10841. PMLR, 2020.
  73. Learning to dispatch for job shop scheduling via deep reinforcement learning. In NeurIPS, volume 33, pp.  1621–1632, 2020.
  74. Learning to solve travelling salesman problem with hardness-adaptive curriculum. In AAAI, 2022.
  75. Learning large neighborhood search for vehicle routing in airport ground handling. IEEE Transactions on Knowledge and Data Engineering, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Jianan Zhou (13 papers)
  2. Yaoxin Wu (26 papers)
  3. Wen Song (24 papers)
  4. Zhiguang Cao (48 papers)
  5. Jie Zhang (847 papers)
Citations (35)
View on Semantic Scholar