Collaboration! Towards Robust Neural Methods for Routing Problems

TL;DR

This paper introduces a collaborative ensemble framework to improve the robustness of neural methods for vehicle routing problems against adversarial attacks and distribution shifts, enhancing performance on both clean and perturbed instances.

Contribution

We propose a novel ensemble-based collaborative training framework that significantly enhances robustness and generalization of neural VRP methods against adversarial perturbations.

Findings

CNF improves robustness against various attacks

It enhances out-of-distribution generalization

The approach is versatile across different neural VRP methods

Abstract

Despite enjoying desirable efficiency and reduced reliance on domain expertise, existing neural methods for vehicle routing problems (VRPs) suffer from severe robustness issues -- their performance significantly deteriorates on clean instances with crafted perturbations. To enhance robustness, we propose an ensemble-based Collaborative Neural Framework (CNF) w.r.t. the defense of neural VRP methods, which is crucial yet underexplored in the literature. Given a neural VRP method, we adversarially train multiple models in a collaborative manner to synergistically promote robustness against attacks, while boosting standard generalization on clean instances. A neural router is designed to adeptly distribute training instances among models, enhancing overall load balancing and collaborative efficacy. Extensive experiments verify the effectiveness and versatility of CNF in defending against various attacks across different neural VRP methods. Notably, our approach also achieves impressive out-of-distribution generalization on benchmark instances.