Timezone: »

Learning to Iteratively Solve Routing Problems with Dual-Aspect Collaborative Transformer
Yining Ma · Jingwen Li · Zhiguang Cao · Wen Song · Le Zhang · Zhenghua Chen · Jing Tang

Wed Dec 08 12:30 AM -- 02:00 AM (PST) @ Virtual

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 efficiency. 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.

Author Information

Yining Ma (National University of Singapore)
Jingwen Li (National University of Singapore)
Zhiguang Cao (Singapore Institute of Manufacturing Technology)
Wen Song (Institute of Marine Scinece and Technology, Shandong University)
Le Zhang (University of Electronic Science and Technology of China)
Zhenghua Chen (Nanyang Technological University)
Jing Tang (The Hong Kong University of Science and Technology)

More from the Same Authors