Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 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

Multi-Task Learning for Routing Problem with Cross-Problem Zero-Shot Generalization (2402.16891v2)

Published 23 Feb 2024 in cs.LG and cs.AI

Abstract: Vehicle routing problems (VRPs), which can be found in numerous real-world applications, have been an important research topic for several decades. Recently, the neural combinatorial optimization (NCO) approach that leverages a learning-based model to solve VRPs without manual algorithm design has gained substantial attention. However, current NCO methods typically require building one model for each routing problem, which significantly hinders their practical application for real-world industry problems with diverse attributes. In this work, we make the first attempt to tackle the crucial challenge of cross-problem generalization. In particular, we formulate VRPs as different combinations of a set of shared underlying attributes and solve them simultaneously via a single model through attribute composition. In this way, our proposed model can successfully solve VRPs with unseen attribute combinations in a zero-shot generalization manner. Extensive experiments are conducted on eleven VRP variants, benchmark datasets, and industry logistic scenarios. The results show that the unified model demonstrates superior performance in the eleven VRPs, reducing the average gap to around 5% from over 20% in the existing approach and achieving a significant performance boost on benchmark datasets as well as a real-world logistics application. The source code is included in https://github.com/FeiLiu36/MTNCO.

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 (52)
  1. Analytics and machine learning in vehicle routing research. International Journal of Production Research 61, 1 (2023), 4–30.
  2. Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940 (2016).
  3. Machine learning for combinatorial optimization: a methodological tour d’horizon. European Journal of Operational Research 290, 2 (2021), 405–421.
  4. Learning Generalizable Models for Vehicle Routing Problems via Knowledge Distillation. arXiv preprint arXiv:2210.07686 (2022).
  5. The vehicle routing problem: State of the art classification and review. Computers & industrial engineering 99 (2016), 300–313.
  6. Xinyun Chen and Yuandong Tian. 2019. Learning to perform local rewriting for combinatorial optimization. Advances in Neural Information Processing Systems 32 (2019).
  7. Gradnorm: Gradient normalization for adaptive loss balancing in deep multitask networks. In International conference on machine learning. PMLR, 794–803.
  8. Select and Optimize: Learning to solve large-scale TSP instances. In Proceedings of The 26th International Conference on Artificial Intelligence and Statistics (Proceedings of Machine Learning Research, Vol. 206), Francisco Ruiz, Jennifer Dy, and Jan-Willem van de Meent (Eds.). PMLR, 1219–1231.
  9. Simulation-guided beam search for neural combinatorial optimization. Advances in Neural Information Processing Systems 35 (2022), 8760–8772.
  10. Ronan Collobert and Jason Weston. 2008. A unified architecture for natural language processing: Deep neural networks with multitask learning. In Proceedings of the 25th international conference on Machine learning. 160–167.
  11. BQ-NCO: Bisimulation Quotienting for Generalizable Neural Combinatorial Optimization. arXiv preprint arXiv:2301.03313 (2023).
  12. VRPSolverEasy: a Python library for the exact solution of a rich vehicle routing problem. (2023).
  13. Towards faster vehicle routing by transferring knowledge from customer representation. IEEE Transactions on Intelligent Transportation Systems 23, 2 (2020), 952–965.
  14. Generalize a small pre-trained model to arbitrarily large tsp instances. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 7474–7482.
  15. Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy. arXiv:2308.14104 [cs.LG]
  16. Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness. arXiv:2110.10942 [cs.LG]
  17. Novel applications of multitask learning and multiple output regression to multiple genetic trait prediction. Bioinformatics 32, 12 (2016), i37–i43.
  18. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770–778.
  19. Keld Helsgaun. 2017. An extension of the Lin-Kernighan-Helsgaun TSP solver for constrained traveling salesman and vehicle routing problems. Roskilde: Roskilde University 12 (2017).
  20. André Hottung and Kevin Tierney. 2019. Neural large neighborhood search for the capacitated vehicle routing problem. arXiv preprint arXiv:1911.09539 (2019).
  21. A generalist neural algorithmic learner. In Learning on Graphs Conference. PMLR, 2–1.
  22. Learning to solve routing problems via distributionally robust optimization. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 36. 9786–9794.
  23. Learning the travelling salesperson problem requires rethinking generalization. Constraints 27, 1-2 (2022), 70–98.
  24. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7482–7491.
  25. Deep policy dynamic programming for vehicle routing problems. In Integration of Constraint Programming, Artificial Intelligence, and Operations Research: 19th International Conference, CPAIOR 2022, Los Angeles, CA, USA, June 20-23, 2022, Proceedings. Springer, 190–213.
  26. Attention, learn to solve routing problems! arXiv preprint arXiv:1803.08475 (2018).
  27. Pomo: Policy optimization with multiple optima for reinforcement learning. Advances in Neural Information Processing Systems 33 (2020), 21188–21198.
  28. An overview and experimental study of learning-based optimization algorithms for the vehicle routing problem. IEEE/CAA Journal of Automatica Sinica 9, 7 (2022), 1115–1138.
  29. Deep reinforcement learning for solving the heterogeneous capacitated vehicle routing problem. IEEE Transactions on Cybernetics 52, 12 (2021), 13572–13585.
  30. Heterogeneous attentions for solving pickup and delivery problem via deep reinforcement learning. IEEE Transactions on Intelligent Transportation Systems 23, 3 (2021), 2306–2315.
  31. Pareto Set Learning for Neural Multi-Objective Combinatorial Optimization. In International Conference on Learning Representations.
  32. On the Generalization of Neural Combinatorial Optimization Heuristics. In Machine Learning and Knowledge Discovery in Databases: European Conference, ECML PKDD 2022, Grenoble, France, September 19–23, 2022, Proceedings, Part V. Springer, 426–442.
  33. Reinforcement learning for solving the vehicle routing problem. Advances in neural information processing systems 31 (2018).
  34. Zero-shot task generalization with multi-task deep reinforcement learning. In International Conference on Machine Learning. PMLR, 2661–2670.
  35. H-TSP: Hierarchically Solving the Large-Scale Traveling Salesman Problem. In AAAI 2023.
  36. Efficient implementation of the genetic algorithm to solve rich vehicle routing problems. Operational Research 21 (2021), 1763–1791.
  37. A generalist agent. arXiv preprint arXiv:2205.06175 (2022).
  38. Independent prototype propagation for zero-shot compositionality. Advances in Neural Information Processing Systems 34 (2021), 10641–10653.
  39. Paolo Toth and Daniele Vigo. 2014. Vehicle routing: problems, methods, and applications. SIAM.
  40. Learning heuristic selection using a time delay neural network for open vehicle routing. In 2017 IEEE Congress on Evolutionary Computation (CEC). Ieee, 1474–1481.
  41. Attention is all you need. Advances in neural information processing systems 30 (2017).
  42. A hybrid genetic algorithm with adaptive diversity management for a large class of vehicle routing problems with time-windows. Computers & operations research 40, 1 (2013), 475–489.
  43. A concise guide to existing and emerging vehicle routing problem variants. European Journal of Operational Research 286, 2 (2020), 401–416.
  44. Pointer networks. Advances in neural information processing systems 28 (2015).
  45. Chenguang Wang and Tianshu Yu. 2023. Efficient Training of Multi-task Neural Solver with Multi-armed Bandits. arXiv:2305.06361 [cs.LG]
  46. Zero-shot learning—a comprehensive evaluation of the good, the bad and the ugly. IEEE transactions on pattern analysis and machine intelligence 41, 9 (2018), 2251–2265.
  47. Visual classification with multitask joint sparse representation. IEEE Transactions on Image Processing 21, 10 (2012), 4349–4360.
  48. Yu Zhang and Qiang Yang. 2021. A survey on multi-task learning. IEEE Transactions on Knowledge and Data Engineering 34, 12 (2021), 5586–5609.
  49. Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problems. IEEE Transactions on Neural Networks and Learning Systems (2022), 1–14. https://doi.org/10.1109/TNNLS.2022.3148435
  50. A hybrid of deep reinforcement learning and local search for the vehicle routing problems. IEEE Transactions on Intelligent Transportation Systems 22, 11 (2020), 7208–7218.
  51. Towards Omni-generalizable Neural Methods for Vehicle Routing Problems. In the 40th International Conference on Machine Learning (ICML 2023).
  52. An accelerated end-to-end method for solving routing problems. Neural Networks (2023).
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Fei Liu (232 papers)
  2. Xi Lin (135 papers)
  3. Qingfu Zhang (78 papers)
  4. Xialiang Tong (14 papers)
  5. Mingxuan Yuan (81 papers)
  6. Zhenkun Wang (34 papers)
Citations (10)
View on Semantic Scholar