{"type":"ScholarlyArticle","title":"Efficient Neural Neighborhood Search for Pickup and Delivery Problems","authors":[{"name":"Yining Ma","slug":"yining-ma","given":"Yining","family":"Ma","affiliation":"National University of Singapore; * STAR"},{"name":"Jingwen Li","slug":"jingwen-li","given":"Jingwen","family":"Li","affiliation":"National University of Singapore; * STAR"},{"name":"Zhiguang Cao","slug":"zhiguang-cao","given":"Zhiguang","family":"Cao","affiliation":"Singapore Institute of Manufacturing Technology , A"},{"name":"Wen Song","slug":"wen-song","given":"Wen","family":"Song","affiliation":"Institute of Marine Science and Technology , Shandong University"},{"name":"Hongliang Guo","slug":"hongliang-guo","given":"Hongliang","family":"Guo","affiliation":"Institute for Infocomm Research , A * STAR"},{"name":"Yuejiao Gong","slug":"yuejiao-gong","given":"Yuejiao","family":"Gong","affiliation":"South China University of Technology"},{"name":"Yeow Meng Chee","slug":"yeow-meng-chee","given":"Yeow Meng","family":"Chee","affiliation":"National University of Singapore"}],"abstract":"We present an efficient Neural Neighborhood Search (N2S) approach for pickup and delivery problems (PDPs). In specific, we design a powerful Synthesis Attention that allows the vanilla self-attention to synthesize various types of features regarding a route solution. We also exploit two customized decoders that automatically learn to perform removal and reinsertion of a pickup-delivery node pair to tackle the precedence constraint. Additionally, a diversity enhancement scheme is leveraged to further ameliorate the performance. Our N2S is generic, and extensive experiments on two canonical PDP variants show that it can produce state-of-the-art results among existing neural methods. Moreover, it even outstrips the well-known LKH3 solver on the more constrained PDP variant. Our implementation for N2S is available online.","doi":"10.24963/ijcai.2022/662","url":"https://ijcai.org/proceedings/2022/662","pdf":"https://ijcai.org/proceedings/2022/0662.pdf","markdown":"https://ijcai.org/proceedings/2022/662.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/662","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Search","track":"Main Track","number":662,"pages":{"first":4776,"last":4784},"keywords":["Multidisciplinary Topics and Applications: Transportation","Search: Search and Machine Learning","Machine Learning: Deep Reinforcement Learning","Search: Local search"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986840","length_sec":84,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984983","length_sec":350,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Accorsi et al., 2022] Luca Accorsi, Andrea Lodi, and Daniele Vigo. Guidelines for the computational testing of machine learning approaches to vehicle routing problems. Operations Research Letters, 50(2):229-234, 2022.","title":"Guidelines for the computational testing of machine learning approaches to vehicle routing problems","authors":"Luca Accorsi, Andrea Lodi, Daniele Vigo","year":"2022","venue":"Operations Research Letters","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Carrabs et al., 2007] Francesco Carrabs, Jean-Franc ¸ois Cordeau, and Gilbert Laporte. Variable neighborhood search for the pickup and delivery traveling salesman problem with LIFO loading. INFORMS Journal on Computing, 19(4):618-632, 2007.","title":"Variable neighborhood search for the pickup and delivery traveling salesman problem with LIFO loading","authors":"Francesco Carrabs, Jean-Franc ¸ois Cordeau, Gilbert Laporte","year":"2007","venue":"INFORMS Journal on Computing","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Chen and Tian, 2019] Xinyun Chen and Yuandong Tian. Learning to perform local rewriting for combinatorial op- timization. In Advances in Neural Information Processing Systems, volume 32, pages 6281-6292, 2019.","title":"Learning to perform local rewriting for combinatorial optimization","authors":"Chen, Tian ; ] Xinyun Chen, Yuandong Tian","year":"2019","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Fu et al., 2021] Zhang-Hua Fu, Kai-Bin Qiu, and Hongyuan Zha. Generalize a small pre-trained model to arbitrarily large TSP instances. In AAAI Conference on Artificial In- telligence, 2021.","title":"Generalize a small pre-trained model to arbitrarily large TSP instances","authors":"Zhang-Hua Fu, Kai-Bin Qiu, Hongyuan Zha","year":"2021","venue":"AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Helsgaun, 2017] Keld Helsgaun. An extension of the lin-kernighan-helsgaun tsp solver for constrained travel- ing salesman and vehicle routing problems. Roskilde: Roskilde University, 2017.","title":"Keld Helsgaun. An extension of the lin-kernighan-helsgaun tsp solver for constrained traveling salesman and vehicle routing problems","authors":"Helsgaun","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Hottung and Tierney, 2020] André Hottung and Kevin Tier- ney. Neural large neighborhood search for the capacitated vehicle routing problem. In European Conference on Ar- tificial Intelligence, 2020.","title":"Neural large neighborhood search for the capacitated vehicle routing problem","authors":"Tierney ; Hottung, André Hottung, Kevin Tierney","year":"2020","venue":"European Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Hottung et al., 2021] André Hottung, Bhanu Bhandari, and Kevin Tierney. Learning a latent search space for routing problems using variational autoencoders. In International Conference on Learning Representations, 2021.","title":"Learning a latent search space for routing problems using variational autoencoders","authors":"Hottung","year":"2021","venue":"International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Joshi et al., 2019] Chaitanya K Joshi, Thomas Laurent, and Xavier Bresson. An efficient graph convolutional net- work technique for the travelling salesman problem. arxiv preprint arxiv: 1906.01227, 2019.","title":"An efficient graph convolutional network technique for the travelling salesman problem","authors":"K Chaitanya, Thomas Joshi, Xavier Laurent, Bresson","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kim et al., 2021] Minsu Kim, Jinkyoo Park, and joungho kim. Learning collaborative policies to solve NP-hard routing problems. In Advances in Neural Information Pro- cessing Systems, volume 34, pages 10418-10430, 2021.","title":"Learning collaborative policies to solve NP-hard routing problems","authors":"Minsu Kim, Jinkyoo Park, Kim","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":10,"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":11,"raw":"[Kool et al., 2021] Wouter Kool, Herke van Hoof, Joaquim Gromicho, and Max Welling. Deep policy dynamic pro- gramming for vehicle routing problems. arxiv preprint arxiv:2102.11756, ArXiv, 2021.","title":"Deep policy dynamic programming for vehicle routing problems","authors":"Wouter Kool, Joaquim Herke Van Hoof, Max Gromicho, Welling","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"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, 2020.","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":"2020","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2011] Yongquan Li, Andrew Lim, Wee-Chong Oon, Hu Qin, and Dejian Tu. The tree representation for the pickup and delivery traveling salesman problem with LIFO loading. European Journal of Operational Research, 212(3):482-496, 2011.","title":"The tree representation for the pickup and delivery traveling salesman problem with LIFO loading","authors":"Yongquan Li, Andrew Lim, Wee-Chong Oon, Dejian Hu Qin, Tu","year":"2011","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Li et al., 2021a] Jingwen Li, Yining Ma, Ruize Gao, Zhiguang Cao, Andrew Lim, Wen Song, and Jie Zhang. Deep reinforcement learning for solving the heteroge- neous capacitated vehicle routing problem. IEEE Trans- actions on Cybernetics, 2021.","title":"Deep reinforcement learning for solving the heterogeneous capacitated vehicle routing problem","authors":"Li","year":"2021","venue":"IEEE Transactions on Cybernetics","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Li et al., 2021b] Jingwen Li, Liang Xin, Zhiguang Cao, An- drew Lim, Wen Song, and Jie Zhang. Heterogeneous at- tentions for solving pickup and delivery problem via deep reinforcement learning. IEEE Transactions on Intelligent Transportation Systems, 2021.","title":"Heterogeneous attentions for solving pickup and delivery problem via deep reinforcement learning","authors":"Li","year":"2021","venue":"IEEE Transactions on Intelligent Transportation Systems","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Li et al., 2021c] Sirui Li, Zhongxia Yan, and Cathy Wu. Learning to delegate for large-scale vehicle routing. In Advances in Neural Information Processing Systems, vol- ume 34, pages 26198-26211, 2021.","title":"Learning to delegate for large-scale vehicle routing","authors":"Li","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ma et al., 2021a] Yi Ma, Xiaotian Hao, Jianye Hao, Jiawen Lu, Xing Liu, Tong Xialiang, Mingxuan Yuan, Zhigang Li, Jie Tang, and Zhaopeng Meng. A hierarchical re- inforcement learning based optimization framework for large-scale dynamic pickup and delivery problems. In Advances in Neural Information Processing Systems, vol- ume 34, pages 23609-23620, 2021.","title":"A hierarchical reinforcement learning based optimization framework for large-scale dynamic pickup and delivery problems","authors":"Ma","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ma et al., 2021b] Yining Ma, Jingwen Li, Zhiguang Cao, Wen Song, Le Zhang, Zhenghua Chen, and Jing Tang. Learning to iteratively solve routing problems with dual- aspect collaborative Transformer. In Advances in Neu- ral Information Processing Systems, volume 34, pages 11096-11107, 2021.","title":"Learning to iteratively solve routing problems with dualaspect collaborative Transformer","authors":"Ma","year":"2021","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Nazari et al., 2018] Mohammadreza Nazari, Afshin Oroo- jlooy, Martin Takáč, and Lawrence V Snyder. Reinforce- ment learning for solving the vehicle routing problem. In Advances in Neural Information Processing Systems, pages 9861-9871, 2018.","title":"Reinforcement learning for solving the vehicle routing problem","authors":"Mohammadreza Nazari, Afshin Oroojlooy, Martin Takáč, Lawrence V Snyder","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Parragh et al., 2008] Sophie N Parragh, Karl F Doerner, and Richard F Hartl. A survey on pickup and delivery prob- lems. Journal für Betriebswirtschaft, 58(2):81-117, 2008.","title":"A survey on pickup and delivery problems","authors":"Karl F Sophie N Parragh, Richard F Doerner, Hartl","year":"2008","venue":"Journal für Betriebswirtschaft","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Renaud et al., 2000] Jacques Renaud, Fayez F Boctor, and Jamal Ouenniche. A heuristic for the pickup and deliv- ery traveling salesman problem. Computers & Operations Research, 27(9):905-916, 2000.","title":"A heuristic for the pickup and delivery traveling salesman problem","authors":"Jacques Renaud, Fayez F Boctor, Jamal Ouenniche","year":"2000","venue":"Computers & Operations Research","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Renaud et al., 2002] Jacques Renaud, Fayez F Boctor, and Gilbert Laporte. Perturbation heuristics for the pickup and delivery traveling salesman problem. Computers & Oper- ations Research, 29(9):1129-1141, 2002.","title":"Perturbation heuristics for the pickup and delivery traveling salesman problem","authors":"Jacques Renaud, Fayez F Boctor, Gilbert Laporte","year":"2002","venue":"Computers & Operations Research","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Savelsbergh, 1990] Martin WP Savelsbergh. An efficient implementation of local search algorithms for constrained routing problems. European Journal of Operational Re- search, 47(1):75-85, 1990.","title":"An efficient implementation of local search algorithms for constrained routing problems","authors":"W P Martin, Savelsbergh","year":"1990","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":24,"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. In Advances in Neural Information Processing Sys- tems, volume 30, pages 6000-6010, 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":25,"raw":"[Veenstra et al., 2017] Marjolein Veenstra, Kees Jan Rood- bergen, Iris FA Vis, and Leandro C Coelho. The pickup and delivery traveling salesman problem with han- dling costs. European Journal of Operational Research, 257(1):118-132, 2017.","title":"The pickup and delivery traveling salesman problem with handling costs","authors":"Marjolein Veenstra, Jan Kees, Iris Fa Roodbergen, Leandro C Vis, Coelho","year":"2017","venue":"European Journal of Operational Research","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wu et al., 2021] Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, and Andrew Lim. Learning improvement heuris- tics for solving routing problems. IEEE Transactions on Neural Networks and Learning Systems, 2021.","title":"Learning improvement heuristics for solving routing problems","authors":"Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, Andrew Lim","year":"2021","venue":"IEEE Transactions on Neural Networks and Learning Systems","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Zhou et al., 2021] Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, and Chen Change Loy. Domain generalization: A survey. arxiv preprint arxiv:2103.02503, ArXiv, 2021.","title":"Domain generalization: A survey","authors":"Kaiyang Zhou, Ziwei Liu, Yu Qiao, Tao Xiang, Chen Change Loy","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}