Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

12-2021

Abstract

Recently, Transformer has become a prevailing deep architecture for solving vehicle routing problems (VRPs). However, it is less effective in learning improvement models for VRP because its positional encoding (PE) method is not suitable in representing VRP solutions. This paper presents a novel Dual-Aspect Collaborative Transformer (DACT) to learn embeddings for the node and positional features separately, instead of fusing them together as done in existing ones, so as to avoid potential noises and incompatible correlations. Moreover, the positional features are embedded through a novel cyclic positional encoding (CPE) method to allow Transformer to effectively capture the circularity and symmetry of VRP solutions (i.e., cyclic sequences). We train DACT using Proximal Policy Optimization and design a curriculum learning strategy for better sample ef®ciency. We apply DACT to solve the traveling salesman problem (TSP) and capacitated vehicle routing problem (CVRP). Results show that our DACT outperforms existing Transformer based improvement models, and exhibits much better generalization performance across different problem sizes on synthetic and benchmark instances, respectively.

Keywords

Benchmarking, Encoding (symbols), Iterative methods, Learning systems, Signal encoding, Traveling salesman problem

Discipline

Databases and Information Systems

Research Areas

Data Science and Engineering

Publication

Proceedings of then 35th Conference on Neural Information Processing Systems, Virtual Conference, 2021 Dec 6-14

Volume

14

First Page

11096

Last Page

11107

ISBN

9781713845393

Identifier

10.48550/arXiv.2110.02544

Publisher

Neural information processing systems foundation

City or Country

California

Copyright Owner and License

Authors

Additional URL

http://doi.org/10.48550/arXiv.2110.02544

Download

Share

COinS