Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 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

Instance-Conditioned Adaptation for Large-scale Generalization of Neural Combinatorial Optimization (2405.01906v1)

Published 3 May 2024 in cs.AI and cs.LG

Abstract: The neural combinatorial optimization (NCO) approach has shown great potential for solving routing problems without the requirement of expert knowledge. However, existing constructive NCO methods cannot directly solve large-scale instances, which significantly limits their application prospects. To address these crucial shortcomings, this work proposes a novel Instance-Conditioned Adaptation Model (ICAM) for better large-scale generalization of neural combinatorial optimization. In particular, we design a powerful yet lightweight instance-conditioned adaptation module for the NCO model to generate better solutions for instances across different scales. In addition, we develop an efficient three-stage reinforcement learning-based training scheme that enables the model to learn cross-scale features without any labeled optimal solution. Experimental results show that our proposed method is capable of obtaining excellent results with a very fast inference time in solving Traveling Salesman Problems (TSPs) and Capacitated Vehicle Routing Problems (CVRPs) across different scales. To the best of our knowledge, our model achieves state-of-the-art performance among all RL-based constructive methods for TSP and CVRP with up to 1,000 nodes.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (50)
  1. Concorde tsp solver, 2006.
  2. Layer normalization. arXiv preprint arXiv:1607.06450, 2016.
  3. Neural combinatorial optimization with reinforcement learning. arXiv preprint arXiv:1611.09940, 2016.
  4. Machine learning for combinatorial optimization: a methodological tour d’horizon. European Journal of Operational Research, 290(2):405–421, 2021.
  5. Dan: Decentralized attention-based neural network for the minmax multiple traveling salesman problem. arXiv preprint arXiv:2109.04205, 2021.
  6. Select and optimize: Learning to aolve large-scale tsp instances. In International Conference on Artificial Intelligence and Statistics, pp.  1219–1231. PMLR, 2023.
  7. Simulation-guided beam search for neural combinatorial optimization. Advances in Neural Information Processing Systems, 35:8760–8772, 2022.
  8. Bq-nco: Bisimulation quotienting for efficient neural combinatorial optimization. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  9. Generalize a small pre-trained model to arbitrarily large tsp instances. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  7474–7482, 2021.
  10. Towards generalizable neural solvers for vehicle routing problems via ensemble with transferrable local policy. arXiv preprint arXiv:2308.14104, 2023.
  11. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.  770–778, 2016.
  12. Helsgaun, K. An extension of the lin-kernighan-helsgaun tsp solver for constrained traveling salesman and vehicle routing problems. Roskilde: Roskilde University, 12, 2017.
  13. Efficient active search for combinatorial optimization problems. In International Conference on Learning Representations, 2022.
  14. Generalize learned heuristics to solve large-scale vehicle routing problems in real-time. In The Eleventh International Conference on Learning Representations, 2022.
  15. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning, pp.  448–456. PMLR, 2015.
  16. Pointerformer: Deep reinforced multi-pointer transformer for the traveling salesman problem. In The Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023.
  17. An efficient graph convolutional network technique for the travelling salesman problem. arXiv preprint arXiv:1906.01227, 2019.
  18. Learning the travelling salesperson problem requires rethinking generalization. arXiv preprint arXiv:2006.07054, 2020.
  19. Learning combinatorial optimization algorithms over graphs. Advances in Neural Information Processing Systems, 30, 2017.
  20. Learning collaborative policies to solve np-hard routing problems. Advances in Neural Information Processing Systems, 34:10418–10430, 2021.
  21. Sym-nco: Leveraging symmetricity for neural combinatorial optimization. Advances in Neural Information Processing Systems, 35:1936–1949, 2022a.
  22. Scale-conditioned adaptation for large scale combinatorial optimization. In NeurIPS 2022 Workshop on Distribution Shifts: Connecting Methods and Applications, 2022b.
  23. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  24. Attention, learn to solve routing problems! In International Conference on Learning Representations, 2019.
  25. Pomo: Policy optimization with multiple optima for reinforcement learning. Advances in Neural Information Processing Systems, 33:21188–21198, 2020.
  26. An overview and experimental study of learning-based optimization algorithms for the vehicle routing problem. IEEE/CAA Journal of Automatica Sinica, 9(7):1115–1138, 2022.
  27. Learning feature embedding refiner for solving vehicle routing problems. IEEE Transactions on Neural Networks and Learning Systems, 2023.
  28. Learning to delegate for large-scale vehicle routing. Advances in Neural Information Processing Systems, 34:26198–26211, 2021.
  29. Evaluating curriculum learning strategies in neural combinatorial optimization. arXiv preprint arXiv:2011.06188, 2020.
  30. Neural combinatorial optimization with heavy decoder: Toward large scale generalization. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  31. On the generalization of neural combinatorial optimization heuristics. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp.  426–442. Springer, 2022.
  32. Reinforcement learning for solving the vehicle routing problem. Advances in neural information processing systems, 31, 2018.
  33. H-tsp: Hierarchically solving the large-scale travelling salesman problem. In Proceedings of the AAAI Conference on Artificial Intelligence, 2023.
  34. Dimes: A differentiable meta solver for combinatorial optimization problems. Advances in Neural Information Processing Systems, 35:25531–25546, 2022.
  35. Meta-sage: Scale meta-learning scheduled adaptation with guided exploration for mitigating scale shift on combinatorial optimization. In International Conference on Machine Learning. PMLR, 2023.
  36. Difusco: Graph-based diffusion solvers for combinatorial optimization. arXiv preprint arXiv:2302.08224, 2023.
  37. New benchmark instances for the capacitated vehicle routing problem. European Journal of Operational Research, 257(3):845–858, 2017.
  38. Instance normalization: The missing ingredient for fast stylization. arXiv preprint arXiv:1607.08022, 2016.
  39. Attention is all you need. Advances in Neural Information Processing Systems, 30, 2017.
  40. Vidal, T. Hybrid genetic search for the cvrp: Open-source implementation and swap* neighborhood. Computers & Operations Research, 140:105643, 2022.
  41. Pointer networks. Advances in neural information processing systems, 28, 2015.
  42. Distance-aware attention reshaping: Enhance generalization of neural solver for large-scale vehicle routing problems. arXiv preprint arXiv:2401.06979, 2024.
  43. Williams, R. J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Machine learning, 8:229–256, 1992.
  44. Distilling autoregressive models to obtain high-performance non-autoregressive solvers for vehicle routing problems with faster inference speed. arXiv preprint arXiv:2312.12469, 2023.
  45. Step-wise deep learning models for solving routing problems. IEEE Transactions on Industrial Informatics, 17(7):4861–4871, 2020.
  46. Multi-decoder attention model with embedding glimpse for solving vehicle routing problems. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pp.  12042–12049, 2021.
  47. A graph neural network assisted monte carlo tree search approach to traveling salesman problem. IEEE Access, 8:108418–108428, 2020.
  48. Glop: Learning global partition and local construction for solving large-scale routing problems in real-time. arXiv preprint arXiv:2312.08224, 2023.
  49. An attention free transformer. arXiv preprint arXiv:2105.14103, 2021.
  50. Towards omni-generalizable neural methods for vehicle routing problems. In International Conference on Machine Learning, 2023.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Changliang Zhou (5 papers)
  2. Xi Lin (135 papers)
  3. Zhenkun Wang (34 papers)
  4. Xialiang Tong (14 papers)
  5. Mingxuan Yuan (81 papers)
  6. Qingfu Zhang (78 papers)
Citations (1)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets