Neural Large Neighborhood Search for the Capacitated Vehicle Routing Problem

TL;DR

This paper introduces a neural large neighborhood search framework that combines learned heuristics with traditional optimization techniques to improve solutions for vehicle routing problems, outperforming existing machine learning methods.

Contribution

It presents a novel neural network-based heuristic integrated into an LNS framework, enhancing vehicle routing problem solutions beyond previous ML approaches.

Findings

Outperforms handcrafted heuristic-based LNS on CVRP with up to 297 customers

Surpasses existing machine learning approaches in vehicle routing tasks

Approaches the performance of state-of-the-art optimization methods

Abstract

Learning how to automatically solve optimization problems has the potential to provide the next big leap in optimization technology. The performance of automatically learned heuristics on routing problems has been steadily improving in recent years, but approaches based purely on machine learning are still outperformed by state-of-the-art optimization methods. To close this performance gap, we propose a novel large neighborhood search (LNS) framework for vehicle routing that integrates learned heuristics for generating new solutions. The learning mechanism is based on a deep neural network with an attention mechanism and has been especially designed to be integrated into an LNS search setting. We evaluate our approach on the capacitated vehicle routing problem (CVRP) and the split delivery vehicle routing problem (SDVRP). On CVRP instances with up to 297 customers, our approach significantly outperforms an LNS that uses only handcrafted heuristics and a well-known heuristic from the literature. Furthermore, we show for the CVRP and the SDVRP that our approach surpasses the performance of existing machine learning approaches and comes close to the performance of state-of-the-art optimization approaches.