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

Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy (2308.14104v3)

Published 27 Aug 2023 in cs.LG

Abstract: Machine learning has been adapted to help solve NP-hard combinatorial optimization problems. One prevalent way is learning to construct solutions by deep neural networks, which has been receiving more and more attention due to the high efficiency and less requirement for expert knowledge. However, many neural construction methods for Vehicle Routing Problems~(VRPs) focus on synthetic problem instances with specified node distributions and limited scales, leading to poor performance on real-world problems which usually involve complex and unknown node distributions together with large scales. To make neural VRP solvers more practical, we design an auxiliary policy that learns from the local transferable topological features, named local policy, and integrate it with a typical construction policy (which learns from the global information of VRP instances) to form an ensemble policy. With joint training, the aggregated policies perform cooperatively and complementarily to boost generalization. The experimental results on two well-known benchmarks, TSPLIB and CVRPLIB, of travelling salesman problem and capacitated VRP show that the ensemble policy significantly improves both cross-distribution and cross-scale generalization performance, and even performs well on real-world problems with several thousand nodes.

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 (42)
  1. Concorde TSP solver. http://www.math.uwaterloo.ca/tsp/concorde/m, 2006.
  2. Efficiently solving very large-scale routing problems. Computers & Operations Research, 107:32–42, 2019.
  3. Neural combinatorial optimization with reinforcement learning. In Proceedings of the 5th International Conference on Learning Representations (ICLR), Toulon, France, 2017.
  4. Machine learning for combinatorial optimization: a methodological tour d’horizon. European Journal of Operational Research, 290(2):405–421, 2021.
  5. Learning generalizable models for vehicle routing problems via knowledge distillation. In Advances in Neural Information Processing Systems 35 (NeurIPS), pages 31226–31238, New Orleans, LA, 2022.
  6. 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 (FOGA), pages 58–71, Potsdam, Germany, 2019.
  7. Combinatorial optimization and reasoning with graph neural networks. Journal of Machine Learning Research, 24(130):1–61, 2023.
  8. Select and optimize: Learning to aolve large-scale TSP instances. In Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (AISTATS), pages 1219–1231, Valencia, Spain, 2023.
  9. Slack induction by string removals for vehicle routing problems. Transportation Science, 54(2):417–433, 2020.
  10. The truck dispatching problem. Management Science, 6(1):80–91, 1959.
  11. BQ-NCO: Bisimulation quotienting for generalizable neural combinatorial optimization. In Advances in Neural Information Processing Systems 36 (NeurIPS), New Orleans, LA, 2023.
  12. Generalize a small pre-trained model to arbitrarily large TSP instances. In Proceedings of the 35th AAAI Conference on Artificial Intelligence (AAAI), pages 7474–7482, Virtual, 2021.
  13. Keld Helsgaun. An effective implementation of the lin–kernighan traveling salesman heuristic. European Journal of Operational Research, 126(1):106–130, 2000.
  14. Keld Helsgaun. An extension of the lin-kernighan-helsgaun TSP solver for constrained traveling salesman and vehicle routing problems. Technical report, 2017.
  15. Generalize learned heuristics to solve large-scale vehicle routing problems in real-time. In Proceedings of the 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, 2023.
  16. Learning to solve routing problems via distributionally robust optimization. In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI), pages 9786–9794, Virtual, 2022.
  17. Multi-view graph contrastive learning for solving vehicle routing problems. In Proceedings of the 39th Conference on Uncertainty in Artificial Intelligence (UAI), pages 984–994, pittsburgh, PA, 2023.
  18. Pointerformer: Deep reinforced multi-pointer transformer for the traveling salesman problem. In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI), pages 8132–8140, Washington, DC, 2023.
  19. An efficient graph convolutional network technique for the travelling salesman problem. arXiv:1906.01227, 2019.
  20. Learning the travelling salesperson problem requires rethinking generalization. Constraints, 27(1-2):70–98, 2022.
  21. Learning combinatorial optimization algorithms over graphs. In Advances in Neural Information Processing Systems 30 (NeurIPS), pages 6348–6358, Long Beach, CA, 2017.
  22. Sym-NCO: Leveraging symmetricity for neural combinatorial optimization. In Advances in Neural Information Processing Systems 35 (NeurIPS), pages 1936–1949, New Orleans, LA, 2022.
  23. Vehicle routing problem and related algorithms for logistics distribution: A literature review and classification. Operational Research, 22(3):2033–2062, 2022.
  24. Attention, learn to solve routing problems! In Proceedings of the 7th International Conference on Learning Representations (ICLR), New Orleans, LA, 2019.
  25. POMO: Policy optimization with multiple optima for reinforcement learning. In Advances in Neural Information Processing Systems 33 (NeurIPS), pages 21188–21198, Virtual, 2020.
  26. From distribution learning in training to gradient search in testing for combinatorial optimization. In Advances in Neural Information Processing Systems 36 (NeurIPS), New Orleans, LA, 2023.
  27. A learning-based iterative method for solving vehicle routing problems. In Proceedings of the 7th International conference on learning representations (ICLR), New Orleans, LA, 2019.
  28. Neural combinatorial optimization with heavy decoder: Toward large scale generalization. In Advances in Neural Information Processing Systems 36 (NeurIPS), New Orleans, LA, 2023.
  29. Learning to search feasible and infeasible regions of routing problems with flexible neural k-opt. In Advances in Neural Information Processing Systems 36 (NeurIPS), New Orleans, LA, 2023.
  30. On the generalization of neural combinatorial optimization heuristics. In Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD), pages 426–442, Grenoble, France, 2022.
  31. Reinforcement learning for solving the vehicle routing problem. In Advances in Neural Information Processing Systems 31 (NeurIPS), pages 9861–9871, Montréal, Canada, 2018.
  32. Gerhard Reinelt. TSPLIB - A traveling salesman problem library. ORSA Journal on Computing, 3(4):376–384, 1991.
  33. Meta-sage: Scale meta-learning scheduled adaptation with guided exploration for mitigating scale shift on combinatorial optimization. In The proceedings of the 40th International Conference on Machine Learning (ICML), pages 32194–32210, Honolulu, Hawaii, 2023.
  34. Stochastic economic lot scheduling via self-attention based deep reinforcement learning. IEEE Transactions on Automation Science and Engineering, pages 1–12, 2023.
  35. DIFUSCO: Graph-based diffusion solvers for combinatorial optimization. In Advances in Neural Information Processing Systems 36 (NeurIPS), New Orleans, LA, 2023.
  36. New benchmark instances for the capacitated vehicle routing problem. European Journal of Operational Research, 257(3):845–858, 2017.
  37. Attention is all you need. In Advances in Neural Information Processing Systems 30 (NeurIPS), pages 5998–6008, Long Beach, CA, 2017.
  38. Thibaut Vidal. Hybrid genetic search for the CVRP: Open-source implementation and swap* neighborhood. Computers & Operations Research, 140:105643, 2022.
  39. Pointer networks. In Advances in Neural Information Processing Systems 28 (NeurIPS), pages 2692–2700, Montreal, Canada, 2015.
  40. Ronald J Williams. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine Learning, 8(3):229–256, 1992.
  41. Learning to dispatch for job shop scheduling via deep reinforcement learning. In Advances in Neural Information Processing Systems 33 (NeurIPS), pages 1621–1632, Vancouver, Canada, 2020.
  42. Towards omni-generalizable neural methods for vehicle routing problems. In Proceedings of the 40th International Conference on Machine Learning (ICML), pages 42769–42789, Honolulu, HI, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Chengrui Gao (13 papers)
  2. Haopu Shang (6 papers)
  3. Ke Xue (28 papers)
  4. Dong Li (429 papers)
  5. Chao Qian (90 papers)
Citations (18)
View on Semantic Scholar
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - gaocrr/ELG (22 stars)