Abstract
There is a surge of interests in recent years to develop graph neural network (GNN) based learning methods for the NP-hard traveling salesman problem (TSP). However, the existing methods not only have limited search space but also require a lot of training instances with ground-truth solutions that are time-consuming to compute. In this paper, we propose a deep bidirectional competitive learning method to address the above issues. The search space is expanded by training multiple weak but complementary models simultaneously, while the sample effiency is significantly improved by devising a gap-aware reweighting scheme over the TSP instances. Specifically, TSP is modeled in a one-by-one construction way by a GNN to assist the heuristic search. Weights are relatively increased for the instances with larger gap between the search algorithm’s solution and the optimal one. The reweighted training set are pipelined to train the next TSP model with strength on the error part. With the error feedback from the search component, multiple complementary GNNs are obtained using this bidirectional alternations. Finally, we present a simple competing strategy by taking the minimum length of the predictions using the multiple TSP models. Experimental results indicate that our method achieves good generalization.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Papadimitriou, C.H.: The Euclidean travelling salesman problem is NP-complete. In: Theoretical Computer Science, pp. 237–244 (1977)
Dai, H., Khalil, E., Zhang, Y., Dilkina, B., Song, L.: Learning combinatorial optimization algorithms over graphs. In: Advances in Neural Information Processing Systems, pp. 6348–6358 (2017)
Kool, W., van Hoof, H., Welling, M.: Attention, learn to solve routing problems! In: International Conference on Learning Representations (2019)
Joshi, C.K., Laurent, T., Bresson, X.: An efficient graph convolutional network technique for the travelling salesman problem (2019). arXiv preprint. arXiv:1906.01227
Wu, Y., Song, W., Cao, Z., Zhang, J., Lim, A.: Learning improvement heuristics for solving routing problems. In: IEEE Transactions on Neural Networks and Learning Systems, pp. 1–13 (2021)
Xu, L.: Deep IA-BI and five actions in circling. In: International Conference on Intelligent Science and Big Data Engineering, pp. 1–21 (2019)
Xu, L.: Deep bidirectional intelligence: AlphaZero, deep IA-search, deep IA-infer, and TPC causal learning. Appl. Inf. 5(1), 1–38 (2018). https://doi.org/10.1186/s40535-018-0052-y
Xu, L.: An overview and perspectives on bidirectional intelligence: lmser duality, double IA harmony, and causal computation. In: IEEE/CAA Journal of Automatica Sinica, pp. 865–893 (2019)
Hopfield, J.J., Tank, D.W.: "Neural" computation of decisions in optimization problems. In: Biological Cybernetics, pp. 141–152 (1985)
Vinyals, O., Fortunato, M., Jaitly, N.: Pointer networks. In: Advances in Neural Information Processing Systems (2015)
Bello, I., Pham, H., Le, Q.V., Norouzi, M., Bengio, S.: Neural combinatorial optimization with reinforcement learning. In: International Conference on Learning Representations, pp. 1–8 (2017)
Xing, Z.H., Tu, S.K.: A graph neural network assisted Monte Carlo tree search approach to traveling salesman problem. In: IEEE Access, pp. 108418–108428 (2020)
Fu, Z.H., Qiu, K.B., Zha, H.: Generalize a small pre-trained model to arbitrarily large TSP instances. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 7474–7482 (2021)
Xin, L., Song, W., Cao, Z., Zhang, J.: NeuroLKH: combining deep learning model with Lin-Kernighan-Helsgaun heuristic for solving the traveling salesman problem. In: Advances in Neural Information Processing Systems, pp. 7472–7483 (2021)
Mersmann, O., Bischl, B., Bossek, J., Trautmann, H., Wagner, M., Neumann, F.: Local search and the traveling salesman problem: a feature-based characterization of problem hardness. In: International Conference on Learning and Intelligent Optimization, pp. 115–129 (2012)
Kool, W., van Hoof, H., Gromicho, J., Welling, M.: Deep policy dynamic programming for vehicle routing problems. In: Integration of Constraint Programming, Artificial Intelligence, and Operations Research (2022)
Deudon, M., Cournut, P., Lacoste, A., Adulyasak, Y., Rousseau, L.M.: Learning heuristics for the tsp by policy gradient. In: Integration of Constraint Programming, Artificial Intelligence, and Operations Research, pp. 170–181 (2018)
Nazari, M., Oroojlooy, A., Snyder, L., Takác, M.: Reinforcement learning for solving the vehicle routing problem. In: Advances in Neural Information Processing Systems (2018)
Ma, Y., Li, J., Cao, Z., Song, W., Zhang, L., Chen, Z., Tang, J.: Learning to iteratively solve routing problems with dual-aspect collaborative transformer. In: Advances in Neural Information Processing Systems, pp. 11096–11107 (2021)
Kwon, Y.D., Choo, J., Kim, B., Yoon, I., Gwon, Y., Min, S.: POMO: policy optimization with multiple optima for reinforcement learning. In: Advances in Neural Information Processing Systems, pp. 21188–21198 (2020)
Zhao, K.X., Tu, S.K., Xu, L.: IA-GM: A deep bidirectional learning method for graph matching. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 3474–3482 (2021)
Rumelhart, D.E., Zipser, D.: Feature discovery by competitive learning. In: Cognitive Science, pp. 75–112 (1985)
Gurobi Optimization, LLC (2022). Gurobi optimizer reference manual. Retrieved from http://www.gurobi.com
Applegate, D., Bixby, R., Chvatal, V., Cook, W. Concorde TSP solver (2006). Retrieved from http://www.math.uwaterloo.ca/tsp/concorde/
Helsgaun, K.: An effective implementation of the lin-kernighan traveling salesman heuristic. In: European journal of operational research, pp. 106–130 (2000)
Freund, Y. and Schapire, R.E.: A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci., 119–139 (1997)
Reinelt, G.: TSPLIB-a traveling salesman problem library. ORSA J. Comput., 376–384 (1991)
Acknowledgement
This work was supported by the National Key R &D Program of China (2018AAA0100700), and Shanghai Municipal Science and Technology Major Project (2021SHZDZX0102).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Ma, H., Tu, S., Xu, L. (2023). IA-CL: A Deep Bidirectional Competitive Learning Method for Traveling Salesman Problem. In: Tanveer, M., Agarwal, S., Ozawa, S., Ekbal, A., Jatowt, A. (eds) Neural Information Processing. ICONIP 2022. Lecture Notes in Computer Science, vol 13623. Springer, Cham. https://doi.org/10.1007/978-3-031-30105-6_44
Download citation
DOI: https://doi.org/10.1007/978-3-031-30105-6_44
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-30104-9
Online ISBN: 978-3-031-30105-6
eBook Packages: Computer ScienceComputer Science (R0)