SHIELD: Multi-task Multi-distribution Vehicle Routing Solver with Sparsity and Hierarchy

TL;DR

SHIELD is a novel multi-task, multi-distribution vehicle routing model that uses sparsity and hierarchy principles to improve efficiency, adaptability, and generalization across diverse real-world routing problems.

Contribution

The paper introduces SHIELD, a new VRP model that incorporates Mixture-of-Depths and hierarchical clustering to handle complex, multi-distribution routing tasks more effectively.

Findings

Outperforms existing methods on 9 real-world maps with 16 VRP variants.

Enhances generalization to unseen distributions and tasks.

Improves efficiency through dynamic node selection and hierarchical representations.

Abstract

Recent advances toward foundation models for routing problems have shown great potential of a unified deep model for various VRP variants. However, they overlook the complex real-world customer distributions. In this work, we advance the Multi-Task VRP (MTVRP) setting to the more realistic yet challenging Multi-Task Multi-Distribution VRP (MTMDVRP) setting, and introduce SHIELD, a novel model that leverages both sparsity and hierarchy principles. Building on a deeper decoder architecture, we first incorporate the Mixture-of-Depths (MoD) technique to enforce sparsity. This improves both efficiency and generalization by allowing the model to dynamically select nodes to use or skip each decoder layer, providing the needed capacity to adaptively allocate computation for learning the task/distribution specific and shared representations. We also develop a context-based clustering layer that exploits the presence of hierarchical structures in the problems to produce better local representations. These two designs inductively bias the network to identify key features that are common across tasks and distributions, leading to significantly improved generalization on unseen ones. Our empirical results demonstrate the superiority of our approach over existing methods on 9 real-world maps with 16 VRP variants each.