Towards Generalizable Neural Solvers for Vehicle Routing Problems via Ensemble with Transferrable Local Policy
This addresses the practical deployment of neural solvers for VRPs, which is crucial for logistics and optimization industries, though it is incremental by enhancing existing methods with ensemble techniques.
The paper tackled the poor generalization of neural construction methods for Vehicle Routing Problems (VRPs) on real-world instances with complex distributions and large scales by designing an ensemble policy that combines a local policy with a global one, resulting in significant improvements in cross-distribution and cross-scale generalization on benchmarks like TSPLIB and CVRPLIB, including handling problems with several thousand nodes.
Machine learning has been adapted to help solve NP-hard combinatorial optimization problems. One prevalent way is learning to construct solutions by deep neural networks, which has been receiving more and more attention due to the high efficiency and less requirement for expert knowledge. However, many neural construction methods for Vehicle Routing Problems~(VRPs) focus on synthetic problem instances with specified node distributions and limited scales, leading to poor performance on real-world problems which usually involve complex and unknown node distributions together with large scales. To make neural VRP solvers more practical, we design an auxiliary policy that learns from the local transferable topological features, named local policy, and integrate it with a typical construction policy (which learns from the global information of VRP instances) to form an ensemble policy. With joint training, the aggregated policies perform cooperatively and complementarily to boost generalization. The experimental results on two well-known benchmarks, TSPLIB and CVRPLIB, of travelling salesman problem and capacitated VRP show that the ensemble policy significantly improves both cross-distribution and cross-scale generalization performance, and even performs well on real-world problems with several thousand nodes.