Dec 6, 2021
Recently, Transformer has become a prevailing deep architecture for solving vehicle routing problems (VRPs). However, the original Transformer is less effective in learning improvement models 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 the original PE, so as to avoid potential noises and incompatible attention scores. Moreover, the positional features are embedded through a novel cyclic positional encoding (CPE) method to capture the circularity and symmetry of VRP solutions. 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 DACT outperforms existing Transformer based improvement models, and exhibits better capability of generalizing across different problem sizes.Recently, Transformer has become a prevailing deep architecture for solving vehicle routing problems (VRPs). However, the original Transformer is less effective in learning improvement models 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 the original PE, so as to avoid…
Account · 1.9k followers
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Professional recording and live streaming, delivered globally.
Presentations on similar topic, category or speaker