{"type":"ScholarlyArticle","title":"A Neural Column Generation Approach to the Vehicle Routing Problem with Two-Dimensional Loading and Last-In-First-Out Constraints","authors":[{"name":"Yifan Xia","slug":"yifan-xia","given":"Yifan","family":"Xia","affiliation":"State Key Laboratory for Novel Software Technology , Nanjing University"},{"name":"Xiangyi Zhang","slug":"xiangyi-zhang","given":"Xiangyi","family":"Zhang","affiliation":"1QB Information Technologies ,; Inc."}],"abstract":"The vehicle routing problem with two-dimensional loading constraints (2L-CVRP) and the last-in-first-out (LIFO) rule presents significant practical and algorithmic challenges. While numerous heuristic approaches have been proposed to address its complexity, stemming from two NP-hard problems: the vehicle routing problem (VRP) and the two-dimensional bin packing problem (2D-BPP), less attention has been paid to developing exact algorithms. Bridging this gap, this article presents an exact algorithm that integrates advanced machine learning techniques, specifically a novel combination of attention and recurrence mechanisms. This integration accelerates the state-of-the-art exact algorithm by a median of 29.79% across various problem instances. Moreover, the proposed algorithm successfully resolves an open instance in the standard test-bed, demonstrating significant improvements brought about by the incorporation of machine learning models. Code is available at https://github.com/xyfffff/NCG-for-2L-CVRP.","doi":"10.24963/ijcai.2024/218","url":"https://ijcai.org/proceedings/2024/218","pdf":"https://ijcai.org/proceedings/2024/0218.pdf","markdown":"https://ijcai.org/proceedings/2024/218.md","bibtex":"https://ijcai.org/proceedings/2024/bibtex/218","volume":{"slug":"2024","title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2024","url":"https://ijcai.org/proceedings/2024/","year":2024,"location":"Jeju, Korea","dates":"3-9 August 2024","editors":"Kate Larson","isbn":"978-1-956792-04-1","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2024"},"section":"Constraint Satisfaction and Optimization","track":"Main Track","number":218,"pages":{"first":1970,"last":1978},"keywords":["Constraint Satisfaction and Optimization: CSO: Constraint optimization problems","Machine Learning: ML: Applications","Multidisciplinary Topics and Applications: MTA: Transportation","Constraint Satisfaction and Optimization: CSO: Modeling"],"videos":[],"references":[{"position":1,"raw":"[Ba et al., 2016] Jimmy Lei Ba, Jamie Ryan Kiros, and Ge- offrey E Hinton. Layer normalization. arXiv preprint arXiv:1607.06450, 2016.","title":"Layer normalization","authors":"Jimmy Lei Ba, Jamie Ryan Kiros, Geoffrey E Hinton","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baldacci et al., 2011] Roberto Baldacci, Aristide Mingozzi, and Roberto Roberti. New route relaxation and pricing strategies for the vehicle routing problem. Operations Re- search, page 1269-1283, Oct 2011.","title":"New route relaxation and pricing strategies for the vehicle routing problem","authors":"Roberto Baldacci, Aristide Mingozzi, Roberto Roberti","year":"2011","venue":"Operations Research","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bengio et al., 2021] Yoshua Bengio, Andrea Lodi, and An- toine Prouvost. Machine learning for combinatorial op- timization: A methodological tour d'horizon. European Journal of Operational Research, 290(2):405-421, 2021.","title":"Machine learning for combinatorial optimization: A methodological tour d'horizon","authors":"Yoshua Bengio, Andrea Lodi","year":"2021","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Brass, 2010] Peter Brass. Advanced Data Structures, page 68-72. Aug 2010.","title":"Peter Brass","authors":"Brass","year":"2010","venue":"Advanced Data Structures","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chi et al., 2022] Cheng Chi, Amine Mohamed Aboussalah, Elias Boutros Khalil, Juyoung Wang, and Zoha Sherkat- Masoumi. A deep reinforcement learning framework for column generation. In Advances in Neural Information Processing Systems, 2022.","title":"A deep reinforcement learning framework for column generation","authors":"Cheng Chi, Mohamed Amine, Elias Boutros Aboussalah, Juyoung Khalil, Zoha Wang, Sherkat-Masoumi","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cho et al., 2014] Kyunghyun Cho, Bart Van Merriënboer, Caglar Gulcehre, Dzmitry Bahdanau, Fethi Bougares, Holger Schwenk, and Yoshua Bengio. Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078, 2014.","title":"Learning phrase representations using rnn encoder-decoder for statistical machine translation","authors":"Cho","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Côté et al., 2020] Jean-Franc ¸ois Côté, Michel Gendreau, and Jean-Yves Potvin. The vehicle routing problem with stochastic two-dimensional items. Transportation Science, 54(2):453-469, 2020.","title":"The vehicle routing problem with stochastic two-dimensional items","authors":"Côté","year":"2020","venue":"Transportation Science","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Côté et al., 2014a] Jean-Franc ¸ois Côté, Mauro Dell'Amico, and Manuel Iori. Combinatorial benders' cuts for the strip packing problem. Operations Research, page 643-661, Jun 2014.","title":"Combinatorial benders' cuts for the strip packing problem","authors":"Côté","year":"2014","venue":"Operations Research","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Côté et al., 2014b] Jean-Franc ¸ois Côté, Michel Gendreau, and Jean-Yves Potvin. An exact algorithm for the two- dimensional orthogonal packing problem with unloading constraints. Operations Research, page 1126-1141, Oct 2014.","title":"An exact algorithm for the twodimensional orthogonal packing problem with unloading constraints","authors":"Côté","year":"2014","venue":"Operations Research","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Desaulniers et al., 2006] Guy Desaulniers, Jacques Desrosiers, and Marius M Solomon. Column gener- ation, volume 5. Springer Science & Business Media, 2006.","title":"Column generation","authors":"Guy Desaulniers, Jacques Desrosiers, Marius M Solomon","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Desrochers and Laporte, 1991] Martin Desrochers and Gilbert Laporte. Improvements and extensions to the miller-tucker-zemlin subtour elimination constraints. Operations Research Letters, 10(1):27-36, 1991.","title":"Improvements and extensions to the miller-tucker-zemlin subtour elimination constraints","authors":"Laporte Desrochers, Martin Desrochers, Gilbert Laporte","year":"1991","venue":"Operations Research Letters","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Fuellerer et al., 2009] Guenther Fuellerer, Karl F. Doerner, Richard F. Hartl, and Manuel Iori. Ant colony optimization for the two-dimensional loading vehicle routing problem. Computers & Operations Research, 36(3):655-673, Mar 2009.","title":"Ant colony optimization for the two-dimensional loading vehicle routing problem","authors":"Guenther Fuellerer, Karl F Doerner, Richard F Hartl, Manuel Iori","year":"2009","venue":"Computers & Operations Research","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Gendreau et al., 2008] Michel Gendreau, Manuel Iori, Gilbert Laporte, and Silvaro Martello. A tabu search heuristic for the vehicle routing problem with two- dimensional loading constraints. Networks: An Interna- tional Journal, 51(1):4-18, 2008.","title":"A tabu search heuristic for the vehicle routing problem with twodimensional loading constraints","authors":"Michel Gendreau, Manuel Iori, Gilbert Laporte, Silvaro Martello","year":"2008","venue":"Networks: An International Journal","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[He et al., 2015] Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun. Deep residual learning for image recognition. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 770-778, 2015.","title":"Deep residual learning for image recognition","authors":"X Kaiming He, Shaoqing Zhang, Jian Ren, Sun","year":"2015","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Iori et al., 2007] Manuel Iori, Juan-José Salazar-González, and Daniele Vigo. An exact approach for the vehicle rout- ing problem with two-dimensional loading constraints. Transportation Science, page 253-264, May 2007.","title":"An exact approach for the vehicle routing problem with two-dimensional loading constraints","authors":"Manuel Iori, Juan-José Salazar-González, Daniele Vigo","year":"2007","venue":"Transportation Science","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Iori et al., 2021] Manuel Iori, Vinícius L. de Lima, Silvano Martello, Flávio K. Miyazawa, and Michele Monaci. Ex- act solution techniques for two-dimensional cutting and packing. European Journal of Operational Research, 289(2):399-415, Mar 2021.","title":"Exact solution techniques for two-dimensional cutting and packing","authors":"Manuel Iori, L Vinícius, Silvano De Lima, Martello, K Flávio, Michele Miyazawa, Monaci","year":"2021","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kim et al., 2022] Minsu Kim, Junyoung Park, and Jinkyoo Park. Sym-NCO: Leveraging symmetricity for neural combinatorial optimization. In Advances in Neural Infor- mation Processing Systems, 2022.","title":"Sym-NCO: Leveraging symmetricity for neural combinatorial optimization","authors":"Minsu Kim, Junyoung Park, Jinkyoo Park","year":"2022","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Kool et al., 2018] Wouter Kool, Herke van Hoof, and Max Welling. Attention, learn to solve routing problems! In International Conference on Learning Representations, 2018.","title":"Attention, learn to solve routing problems!","authors":"Wouter Kool, Herke Van Hoof, Max Welling","year":"2018","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Kwon et al., 2020] Yeong-Dae Kwon, Jinho Choo, By- oungjip Kim, Iljoo Yoon, Youngjune Gwon, and Seungjai Min. Pomo: Policy optimization with multiple optima for reinforcement learning. In Advances in Neural Informa- tion Processing Systems, volume 33, pages 21188-21198.","title":"Pomo: Policy optimization with multiple optima for reinforcement learning","authors":"Yeong-Dae Kwon, Jinho Choo, Byoungjip Kim, Iljoo Yoon, Youngjune Gwon, Seungjai Min","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"Curran Associates, Inc., 2020.","title":null,"authors":"Curran Associates, Inc","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Morabit et al., 2021] Mouad Morabit, Guy Desaulniers, and Andrea Lodi. Machine-learning-based column selec- tion for column generation. Transportation Science, 55(4):815-831, 2021.","title":"Mouad Morabit, Guy Desaulniers, and Andrea Lodi. Machine-learning-based column selection for column generation","authors":"Morabit","year":"2021","venue":"Transportation Science","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Morabit et al., 2023] Mouad Morabit, Guy Desaulniers, and Andrea Lodi. Machine-learning-based arc selection for constrained shortest path problems in column generation. INFORMS Journal on Optimization, 5(2):191-210, 2023.","title":"Machine-learning-based arc selection for constrained shortest path problems in column generation","authors":"Morabit","year":"2023","venue":"INFORMS Journal on Optimization","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Pinto et al., 2013] Telmo Pinto, Cláudio Alves, and J Valério de Carvalho. Column generation based heuristic for a vehicle routing problem with 2-dimensional loading constraints: a prototype. In XI Congresso Galego de Estatística e Investigación de Operacións, Spain, 2013.","title":"Column generation based heuristic for a vehicle routing problem with 2-dimensional loading constraints: a prototype","authors":"Pinto","year":"2013","venue":"XI Congresso Galego de Estatística e Investigación de Operacións","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Pinto et al., 2015] Telmo Pinto, Cláudio Alves, and José Valério de Carvalho. Variable neighborhood search for the elementary shortest path problem with loading constraints. In Computational Science and Its Applications-ICCSA 2015: 15th International Confer- ence, Banff, AB, Canada, June 22-25, 2015, Proceedings, Part II 15, pages 474-489. Springer, 2015.","title":"Variable neighborhood search for the elementary shortest path problem with loading constraints","authors":"Pinto","year":"2015","venue":"Computational Science and Its Applications-ICCSA 2015: 15th International Conference","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Pinto et al., 2016] Telmo Pinto, Cláudio Alves, and José Valério de Carvalho. A branch-and-price algorithm for the vehicle routing problem with 2-dimensional loading constraints. In International Conference on Computational Logistics, pages 321-336. Springer, 2016.","title":"A branch-and-price algorithm for the vehicle routing problem with 2-dimensional loading constraints","authors":"Pinto","year":"2016","venue":"International Conference on Computational Logistics","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Pollaris et al., 2015] Hanne Pollaris, Kris Braekers, An Caris, Gerrit K. Janssens, and Sabine Limbourg. Vehicle routing problems with loading constraints: state-of-the-art and future directions. OR Spectrum, 37(2):297-330, Mar 2015.","title":"Vehicle routing problems with loading constraints: state-of-the-art and future directions","authors":"Hanne Pollaris, Kris Braekers, An Caris, Gerrit K Janssens, Sabine Limbourg","year":"2015","venue":"OR Spectrum","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Shen et al., 2022] Yunzhuang Shen, Yuan Sun, Xiaodong Li, Andrew Eberhard, and Andreas Ernst. Enhancing column generation by a machine-learning-based pricing heuristic for graph coloring. In Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022, volume 36, pages 9926-9934, United States of America, June 2022.","title":"Enhancing column generation by a machine-learning-based pricing heuristic for graph coloring","authors":"Yunzhuang Shen, Yuan Sun, Xiaodong Li, Andrew Eberhard, Andreas Ernst","year":"2022","venue":"Proceedings of the 36th AAAI Conference on Artificial Intelligence, AAAI 2022","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Vaswani et al., 2017] Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. Advances in neural information processing systems, 30, 2017.","title":"Attention is all you need","authors":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, Illia Polosukhin","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Wang et al., 2009] Fan Wang, Yi Tao, and Ning Shi. A sur- vey on vehicle routing problem with loading constraints. 2009 International Joint Conference on Computational Sciences and Optimization, 2:602-606, 2009.","title":"A survey on vehicle routing problem with loading constraints","authors":"Fan Wang, Yi Tao, Ning Shi","year":"2009","venue":"International Joint Conference on Computational Sciences and Optimization","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Wei et al., 2018] Lijun Wei, Zhenzhen Zhang, Defu Zhang, and Stephen C.H. Leung. A simulated annealing algo- rithm for the capacitated vehicle routing problem with two-dimensional loading constraints. European Journal of Operational Research, page 843-859, Mar 2018.","title":"A simulated annealing algorithm for the capacitated vehicle routing problem with two-dimensional loading constraints","authors":"Lijun Wei, Zhenzhen Zhang, Defu Zhang, Stephen C H Leung","year":"2018","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Yuan et al., 2023] Haofeng Yuan, Lichang Fang, and Shiji Song. A reinforcement-learning-based multiple-column selection strategy for column generation. arXiv preprint arXiv:2312.14213, 2023.","title":"A reinforcement-learning-based multiple-column selection strategy for column generation","authors":"Yuan","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Zachariadis et al., 2009] Emmanouil E. Zachariadis, Chris- tos D. Tarantilis, and Christos T. Kiranoudis. A guided tabu search for the vehicle routing problem with two- dimensional loading constraints. European Journal of Op- erational Research, 195(3):729-743, Jun 2009.","title":"A guided tabu search for the vehicle routing problem with twodimensional loading constraints","authors":"E Emmanouil, Christos D Zachariadis, Christos T Tarantilis, Kiranoudis","year":"2009","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhang et al., 2022a] Xiangyi Zhang, Lu Chen, Michel Gen- dreau, and André Langevin. A branch-and-cut algorithm for the vehicle routing problem with two-dimensional loading constraints. European Journal of Operational Re- search, 302(1):259-269, 2022.","title":"A branch-and-cut algorithm for the vehicle routing problem with two-dimensional loading constraints","authors":"Zhang","year":"2022","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhang et al., 2022b] Xiangyi Zhang, Lu Chen, Michel Gen- dreau, and André Langevin. A branch-and-price-and- cut algorithm for the vehicle routing problem with two- dimensional loading constraints. Transportation Science, 56(6):1618-1635, 2022.","title":"A branch-and-price-andcut algorithm for the vehicle routing problem with twodimensional loading constraints","authors":"Zhang","year":"2022","venue":"Transportation Science","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zhang et al., 2022c] Xiangyi Zhang, Lu Chen, Michel Gen- dreau, and André Langevin. Learning-based branch-and- price algorithms for the vehicle routing problem with time windows and two-dimensional loading constraints. IN- FORMS Journal on Computing, 34(3):1419-1436, 2022.","title":"Learning-based branch-andprice algorithms for the vehicle routing problem with time windows and two-dimensional loading constraints","authors":"Zhang","year":"2022","venue":"IN-FORMS Journal on Computing","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zong et al., 2021] Zefang Zong, Tao Feng, Tong Xia, De- peng Jin, and Yong Li. Deep reinforcement learning for demand driven services in logistics and transportation sys- tems: A survey. arXiv preprint arXiv:2108.04462, 2021.","title":"Deep reinforcement learning for demand driven services in logistics and transportation systems: A survey","authors":"Zefang Zong, Tao Feng, Tong Xia, Depeng Jin, Yong Li","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}