Cross-Problem Learning for Solving Vehicle Routing Problems

Among the studied COPs, the Vehicle Routing Problems (VRPs) are often favoured and chosen to verify the effectiveness Existing neural heuristics often train a deep architecture of the NCO methods, especially the Traveling from scratch for each specific vehicle Salesman Problem (TSP) and Capacitated Vehicle Routing routing problem (VRP), ignoring the transferable Problem (CVRP). On the one hand, VRPs are widely applied knowledge across different VRP variants. This paper in real-world scenarios such as logistics, and drone proposes the cross-problem learning to assist delivery [Wang and Sheu, 2019; Konstantakopoulos et al., heuristics training for different downstream VRP 2022]. On the other hand, VRPs are known to be NPcomplete variants. Particularly, we modularize neural architectures problems, and many of them are challenging to be for complex VRPs into 1) the backbone solved efficiently. With the advances of deep learning and its Transformer for tackling the travelling salesman power to automatically learn neural heuristics, NCO methods problem (TSP), and 2) the additional lightweight have demonstrated notable promise against traditional heuristics modules for processing problem-specific features [Kool et al., 2018; Kwon et al., 2020; Li et al., 2021; Luo in complex VRPs. Accordingly, we propose to pretrain et al., 2023]. To further strengthen NCO methods, a number the backbone Transformer for TSP, and then of recent endeavors have been paid to enhance generalization apply it in the process of fine-tuning the Transformer capabilities, which attempt to ameliorate the performance of models for each target VRP variant. On the the neural heuristics in solving the VRP instances with distributions one hand, we fully fine-tune the trained backbone or sizes unseen during training [Geisler et al., 2022; Transformer and problem-specific modules simultaneously.