Multi-View Graph Contrastive Learning for Solving Vehicle Routing Problems

Yuan Jiang, Zhiguang Cao, Yaoxin Wu, Jie Zhang

Keywords: Vehicle Routing Problem, Combinatorial Optimization Problem, Deep Reinforcement Learning, Contrastive Learning

TL;DR: A multi-view graph contrasting learning (MVGCL) approach to tackle out-of-distribution (o.o.d.) issue in routing problem, which couples a graph pattern learner in a self-supervised fashion with deep reinforcement learning.

Abstract: Recently, neural heuristics based on deep learning have reported encouraging results for solving vehicle routing problems (VRPs), especially on independent and identically distributed (i.i.d.) instances, e.g. uniform. However, in the presence of a distribution shift for the testing instances, their performance becomes considerably inferior. In this paper, we propose a multi-view graph Contrastive learning (MVGCL) approach to enhance the generalization across different distributions, which exploits two graph pattern learners in a self-supervised fashion to facilitate a neural heuristic equipped with an active search scheme. Specifically, we first propose two augmentation methods that are specially designed for routing problems, and our MVGCL leverages graph contrastive learning to extract transferable patterns from VRP graphs to attain the generalizable multi-view (i.e. node and graph) representation. Then it adopts the learnt node embedding and graph embedding to assist the neural heuristic and the active search (during inference) for route construction, respectively. Extensive experiments on randomly generated VRP instances from various distributions, and the ones from TSPLib and CVRPLib show that our MVGCL is superior to the baselines in boosting the cross-distribution generalization performance.