Deep Graph Representation Learning to Solve Vehicle Routing Problem | IEEE Conference Publication | IEEE Xplore

Deep Graph Representation Learning to Solve Vehicle Routing Problem


Abstract:

The performance of a neural network relies on the depth of a model to learn the structural correlations of the features. Nevertheless, Graph Neural Networks (GNN) tends t...Show More

Abstract:

The performance of a neural network relies on the depth of a model to learn the structural correlations of the features. Nevertheless, Graph Neural Networks (GNN) tends to lose its efficiency as the depth increases. In this paper we propose a technique to alleviate this problem by building on the existing GNN architecture. In effect, we installed a gating mechanism to overcome the propagation of noise information across the layers and trained the model using a proximal policy optimization (PPO), a policy gradient-based reinforcement learning algorithm. We trained the proposed model on a capacitated vehicle routing problem (CVRP) datasets generated on the fly. We used an encoder-decoder framework where the encoder learns the representation of the graph structured CVRP instance and the decoder learns to construct an optimal route based on the reward function designed. According to experiments using randomly generated test instances, the proposed model produces better results than the current deep reinforcement learning (DRL) methods to solve CVRP. To confirm the performance of our model, we also tested using locally generated real-world data parsed from digital maps. The results affirms that our model performs well in both random instance testing and real-world instance testing.
Date of Conference: 09-11 July 2023
Date Added to IEEE Xplore: 28 November 2023
ISBN Information:

ISSN Information:

Conference Location: Adelaide, Australia

Funding Agency:

References is not available for this document.

1. Introduction

The performance of a neural network relies on the depth of a model to learn the structural correlations of the features [1]. Correspondingly, the performance of graph neural networks (GNN), heavily relies on the ability to train deep networks. Nevertheless, due to the possible reasons of over fitting, vanishing gradient and over squashing, GNNs suffer from decreasing performance as the number of layers increases which restricts the amount of information propagation between nodes [2]. On the other hand, providing optimal solutions to combinatorial optimization problems such as Capacitated Vehicle Routing Problems (CVRP) plays an important role in intelligent transportation system [3]. Classical solutions of CVRP fall into categories of heuristic [4], approximate [5], and exact approaches. Heuristic algorithms are known to have good computation performance though they have the drawback of lacking a theoretical guarantee. Moreover, they also require frequent customization and domain-specific knowledge which makes them unable to support large-scale optimization tasks. Exact approaches can provide optimal solutions although they are inherently computation-intensive which makes them unsuitable to solve large-scale problems. On the other hand, approximate algorithms can usually obtain quality-guaranteed solutions, yet they can only offer weaker optimality warrants compared to exact algorithms [6].

Select All
1.
R. K. Srivastava, K. Greff, and J. Schmidhuber, “Highway Networks,” May 2015, [Online]. Available: http://arxiv.org/abs/1505.00387.
2.
D. Bau, J.-Y. Zhu, H. Strobelt, A. Lapedriza, B. Zhou, and A. Torralba, “Understanding the role of individual units in a deep neural network,” Proceedings of the National Academy of Sciences, vol. 117, no. 48, pp. 30071–30078, Dec. 2020, doi: 10.1073/pnas.1907375117.
3.
G. Dimitrakopoulos and P. Demestichas, “Intelligent transportation systems: Systems based on cognitive networking principles and management functionality,” IEEE Vehicular Technology Magazine, vol. 5, no. 1, pp. 77–84, Mar. 2010, doi: 10.1109/MVT.2009.935537.
4.
N. Bianchessi and G. Righini, “Heuristic algorithms for the vehicle routing problem with simultaneous pick-up and delivery,” Comput Oper Res, vol. 34, no. 2, pp. 578–594, Feb. 2007, doi: 10.1016/j.cor.2005.03.014.
5.
S. O. Krumke, S. Saliba, T. Vredeveld, and S. Westphal, “Approximation algorithms for a vehicle routing problem,” Mathematical Methods of Operations Research, vol. 68, no. 2, pp. 333–359, Oct. 2008, doi: 10.1007/s00186-008-0224-y.
6.
J. Park, J. Chun, S. H. Kim, Y. Kim, and J. Park, “Learning to schedule job-shop problems: representation and policy learning using graph neural network and reinforcement learning,” Int J Prod Res, vol. 59, no. 11, pp. 3360–3377, Jun. 2021, doi: 10.1080/00207543.2020.1870013.
7.
D. Bahdanau, K. Cho, and Y. Bengio, “Neural Machine Translation by Jointly Learning to Align and Translate,” Sep. 2014, [Online]. Available: http://arxiv.org/abs/1409.0473.
8.
K. Lei, P. Guo, Y. Wang, X. Wu, and W. Zhao, “Solve routing problems with a residual edge-graph attention neural network,” May 2021, [Online]. Available: http://arxiv.org/abs/2105.02730.
9.
H. Dai, E. B. Khalil, Y. Zhang, B. Dilkina, and L. Song, “Learning Combinatorial Optimization Algorithms over Graphs,” Apr. 2017, [Online]. Available: http://arxiv.org/abs/1704.01665.
10.
G. Fellek, A. Farid, G. Gebreyesus, S. Fujimura, and O. Yoshie, “Graph Transformer with Reinforcement Learning for Vehicle Routing Problem,” IEEJ Transactions on Electrical and Electronic Engineering, Feb. 2023, doi: 10.1002/tee.23771.
11.
O. Vinyals, M. Fortunato, and N. Jaitly, “Pointer Networks,” in Proc. Adv. Neural Inf. Process. Syst. (NeurIPS), 2015, pp. 2692–2700.
12.
I. Bello, H. Pham, Q. V. Le, M. Norouzi, and S. Bengio, “Neural Combinatorial Optimization with Reinforcement Learning,” in International Conference on Learning Representations, Nov. 2017. [Online]. Available: http://arxiv.org/abs/1611.09940.
13.
Y. Xu, M. Fang, L. Chen, G. Xu, Y. Du, and C. Zhang, “Reinforcement Learning With Multiple Relational Attention for Solving Vehicle Routing Problems,” IEEE Trans Cybern, 2021, doi: 10.1109/TCYB.2021.3089179.
14.
Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and P. S. Yu, “A Comprehensive Survey on Graph Neural Networks,” IEEE Trans Neural Netw Learn Syst, vol. 32, no. 1, pp. 4–24, Jan. 2021, doi: 10.1109/TNNLS.2020.2978386.
15.
Ashish Vaswani, “Attention is all you need,” in of Advances in Neural Information Processing Systems 30 (NIPS 2017), 2017, pp. 5998–6008.
16.
S. Brody, U. Alon, and E. Yahav, “How Attentive are Graph Attention Networks?,” May 2021, [Online]. Available: http://arxiv.org/abs/2105.14491.
17.
J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal Policy Optimization Algorithms,” Jul. 2017, [Online]. Available: http://arxiv.org/abs/1707.06347.
18.
M. Haklay and P. Weber, “OpenStreetMap: User-Generated Street Maps,” IEEE Pervasive Comput, vol. 7, no. 4, pp. 12–18, Oct. 2008, doi: 10.1109/MPRV.2008.80.
19.
P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Liò, and Y. Bengio, “Graph Attention Networks,” in International Conference on Learning Representations, 2017, Oct. 2017.
20.
T. N. Kipf and M. Welling, “Semi-Supervised Classification with Graph Convolutional Networks,” Sep. 2016, [Online]. Available: http://arxiv.org/abs/1609.02907.
21.
Mohammadreza Nazari, Afshin Oroojlooy, Lawrence V. Snyder, and Martin TaḱǍ, “Neural combinatorial optimization with reinforcement learning,” in Proceedings of the 32nd International Conference on Neural Information Processing SystemsDecember 2018, Dec. 2018, pp. 9861–9871.
22.
M. Deudon, P. Cournut, A. Lacoste, Y. Adulyasak, and L.-M. Rousseau, “Learning Heuristics for the TSP by Policy Gradient,” 2018, pp. 170–181. doi: 10.1007/978-3-319-93031-2_12.
23.
P. Emami and S. Ranka, “Learning Permutations with Sinkhorn Policy Gradient,” May 2018, [Online]. Available: http://arxiv.org/abs/1805.07010.
24.
W. Kool, Van Hoof, and M. Welling, “Attention, learn to solve routing problems,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2019, pp. 1–25.
25.
G. Fellek, G. Gebreyesus, A. Farid, S. Fujimura, and O. Yoshie, “Edge Encoded Attention Mechanism to Solve Capacitated Vehicle Routing Problem with Reinforcement Learning,” in 2022 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), IEEE, Dec. 2022, pp. 576–582. doi: 10.1109/IEEM55944.2022.9989997.
26.
S. Guo, Y. Xiao, and L. Niu, “GGTAN: Graph gated talking-heads attention networks for traveling salesman problem,” in Proceedings - 2020 IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology, WI-IAT 2020, Institute of Electrical and Electronics Engineers Inc., Dec. 2020, pp. 676–681. doi: 10.1109/WIIAT50758.2020.00102.
27.
J. Zhao, M. Mao, X. Zhao, and J. Zou, “A Hybrid of Deep Reinforcement Learning and Local Search for the Vehicle Routing Problems,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 11, pp. 7208–7218, Nov. 2021, doi: 10.1109/TITS.2020.3003163.
28.
L. Duan, “Efficiently Solving the Practical Vehicle Routing Problem: A Novel Joint Learning Approach,” in Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery, Aug. 2020, pp. 3054–3063. doi: 10.1145/3394486.3403356.
29.
K. Zhang, F. He, Z. Zhang, X. Lin, and M. Li, “Multi-vehicle routing problems with soft time windows: A multi-agent reinforcement learning approach,” Transp Res Part C Emerg Technol, vol. 121, Dec. 2020, doi: 10.1016/j.trc.2020.102861.
30.
L. Xin, W. Song, Z. Cao, and J. Zhang, “Multi-Decoder Attention Model with Embedding Glimpse for Solving Vehicle Routing Problems,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 13, pp. 12042–12049, May 2021, doi: 10.1609/aaai.v35i13.17430.

Contact IEEE to Subscribe

References

References is not available for this document.