Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 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 Backdoors for Mixed Integer Linear Programs with Contrastive Learning (2401.10467v2)

Published 19 Jan 2024 in cs.AI, cs.LG, and math.OC

Abstract: Many real-world problems can be efficiently modeled as Mixed Integer Linear Programs (MILPs) and solved with the Branch-and-Bound method. Prior work has shown the existence of MILP backdoors, small sets of variables such that prioritizing branching on them when possible leads to faster running times. However, finding high-quality backdoors that improve running times remains an open question. Previous work learns to estimate the relative solver speed of randomly sampled backdoors through ranking and then decide whether to use the highest-ranked backdoor candidate. In this paper, we utilize the Monte-Carlo tree search method to collect backdoors for training, rather than relying on random sampling, and adapt a contrastive learning framework to train a Graph Attention Network model to predict backdoors. Our method, evaluated on several common MILP problem domains, demonstrates performance improvements over both Gurobi and previous models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (47)
  1. Set covering algorithms using cutting planes, heuristics, and subgradient optimization: a computational study. In Combinatorial Optimization, pages 37–60. Springer, 1980.
  2. How attentive are graph attention networks? arXiv preprint arXiv:2105.14491, 2021.
  3. A simple framework for contrastive learning of visual representations. In International conference on machine learning, pages 1597–1607. PMLR, 2020.
  4. Learning to schedule heuristics in branch and bound. Advances in Neural Information Processing Systems, 34:24235–24246, 2021.
  5. Backdoors in the context of learning. In International Conference on Theory and Applications of Satisfiability Testing, pages 73–79. Springer, 2009.
  6. Augment with care: Contrastive learning for combinatorial problems. In International Conference on Machine Learning, pages 5627–5642. PMLR, 2022.
  7. On the evolution of random graphs. Publ. math. inst. hung. acad. sci, 5(1):17–60, 1960.
  8. Learning pseudo-backdoors for mixed integer programs, 2021.
  9. Backdoor branching. In International Conference on Integer Programming and Combinatorial Optimization, pages 183–191. Springer, 2011.
  10. Mixed integer linear programming in process scheduling: Modeling, algorithms, and applications. Annals of Operations Research, 139:131–162, 2005.
  11. Exact combinatorial optimization with graph convolutional neural networks. Advances in neural information processing systems, 32, 2019.
  12. Algorithms for the multi-resource generalized assignment problem. Management science, 37(6):695–713, 1991.
  13. Hybrid models for learning to branch. Advances in neural information processing systems, 33:18087–18097, 2020.
  14. Gurobi Optimization, LLC. Gurobi Optimizer Reference Manual, 2023.
  15. A gnn-guided predict-and-search framework for mixed-integer linear programming. In ICLR, 2022.
  16. Learning to search in branch and bound algorithms. Advances in neural information processing systems, 27, 2014.
  17. Learning deep representations by mutual information estimation and maximization. arXiv preprint arXiv:1808.06670, 2018.
  18. Forest harvesting and minimum cuts: a new approach to handling spatial constraints. Forest Science, 43(4):544–554, 1997.
  19. Searching large neighborhoods for integer linear programs with contrastive learning. In International Conference on Machine Learning, pages 13869–13890. PMLR, 2023.
  20. A survey on contrastive self-supervised learning. Technologies, 9(1):2, 2020.
  21. Learning to branch in mixed integer programming. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 30, 2016.
  22. Learning to run heuristics in tree search. In Ijcai, pages 659–666, 2017.
  23. Finding backdoors to integer programs: a monte carlo tree search framework. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, pages 3786–3795, 2022.
  24. Supervised contrastive learning. Advances in neural information processing systems, 33:18661–18673, 2020.
  25. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  26. Computation of renameable horn backdoors. In Theory and Applications of Satisfiability Testing–SAT 2008: 11th International Conference, SAT 2008, Guangzhou, China, May 12-15, 2008. Proceedings 11, pages 154–160. Springer, 2008.
  27. Learning to compare nodes in branch and bound with graph neural networks. Advances in Neural Information Processing Systems, 35:32000–32010, 2022.
  28. An automatic method for solving discrete programming problems. Springer, 2010.
  29. Towards a universal test suite for combinatorial auction algorithms. In Proceedings of the 2nd ACM conference on Electronic commerce, pages 66–76, 2000.
  30. An efficient framework for learning sentence representations. arXiv preprint arXiv:1803.02893, 2018.
  31. Contrastive losses and solution caching for predict-and-optimize. arXiv preprint arXiv:2011.05354, 2020.
  32. Solving mixed integer programs using neural networks. arXiv preprint arXiv:2012.13349, 2020.
  33. Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748, 2018.
  34. Computing horn strong backdoor sets thanks to local search. In 2006 18th IEEE International Conference on Tools with Artificial Intelligence (ICTAI’06), pages 139–143. IEEE, 2006.
  35. Learning to cut by looking ahead: Cutting plane selection via imitation learning. In International conference on machine learning, pages 17584–17600. PMLR, 2022.
  36. Ira Pohl. Heuristic search viewed as path finding in a graph. Artificial intelligence, 1(3-4):193–204, 1970.
  37. Learning to search via retrospective imitation. arXiv preprint arXiv:1804.00846, 2018.
  38. A general large neighborhood search framework for solving integer linear programs. Advances in Neural Information Processing Systems, 33:20012–20023, 2020.
  39. Learning a large neighborhood search algorithm for mixed integer programs. arXiv preprint arXiv:2107.10201, 2021.
  40. Reinforcement learning for integer programming: Learning to cut. In International conference on machine learning, pages 9367–9376. PMLR, 2020.
  41. Finding a maximum independent set. SIAM Journal on Computing, 6(3):537–546, 1977.
  42. Directed graph contrastive learning. Advances in neural information processing systems, 34:19580–19593, 2021.
  43. The vehicle routing problem. SIAM, 2002.
  44. Graph attention networks. arXiv preprint arXiv:1710.10903, 2017.
  45. Backdoors to typical case complexity. In IJCAI, volume 3, pages 1173–1178, 2003.
  46. Graph contrastive learning with augmentations. Advances in neural information processing systems, 33:5812–5823, 2020.
  47. A survey for solving mixed integer programming via machine learning. Neurocomputing, 519:205–217, 2023.

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