Enhancing generalization in large-scale HCVRP: A rank-augmented neural solver
Publication Type
Conference Proceeding Article
Publication Date
8-2025
Abstract
The Heterogeneous Capacitated Vehicle Routing Problem (HCVRP) is an NP-hard combinatorial optimization problem. State-of-the-art neural solvers face difficulties in generalizing to large-scale scenarios after training on small-scale instances. Our experiments reveal that performance degradation is primarily due to the low-rank nature of attention matrix in large-scale instances. This results in insufficient distinction among node features, impacting the accuracy of Markov Decision Processes. Additionally, these models utilize self-attention for vehicle information interaction, but overly incorporate features from others, which suppresses individual features and leads to a deviation from the optimal route. To address these challenges, we propose the Rank-Augmented Neural Solver (RANS), which introduces two key innovations: 1) A simple yet effective mechanism to increase and approximate the upper bound of the attention matrix's rank, enabling the generation of more distinctive node features. 2) A Dual Cross-Attention Module within the vehicle encoder that accurately captures each vehicle's optimal routes while maintaining balanced vehicle collaboration. The experimental results show that RANS performs favorably against the baselines. Notably, when applied to instances with up to 10,000 nodes, RANS achieves an inference time that is merely 13.42% of the best baseline among the neural solvers, while simultaneously reducing the min-max travel time by 23.72%.
Keywords
attention mechanism, combinatorial optimization, heterogeneous CVRP, rank-augmented, reinforcement learning
Discipline
Artificial Intelligence and Robotics | Databases and Information Systems
Research Areas
Intelligent Systems and Optimization
Publication
KDD '25: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, Toronto, Canada, 2025 August 3-7
Volume
2
First Page
1845
Last Page
1856
ISBN
9798400714542
Identifier
10.1145/3711896.3736935
Publisher
ACM
City or Country
New York
Citation
LIU, Qidong; LIAN, Jiurui; LIU, Chaoyue; and CAO, Zhiguang.
Enhancing generalization in large-scale HCVRP: A rank-augmented neural solver. (2025). KDD '25: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, Toronto, Canada, 2025 August 3-7. 2, 1845-1856.
Available at: https://ink.library.smu.edu.sg/sis_research/10575
Additional URL
https://doi.org/10.1145/3711896.3736935