Hybrid Node-Destroyer Model with Large Neighborhood Search for Solving the Capacitated Vehicle Routing Problem

2025-08-12

AI Summary

For the Capacitated Vehicle Routing Problem (CVRP), this paper proposes a metaheuristic iterative optimization framework integrating Graph Neural Networks (GNNs) with Large Neighborhood Search (LNS). The core contribution is a lightweight, scale-invariant Node-Destroyer model that leverages graph-structured problem information to intelligently select nodes for removal—enabling zero-shot transfer across problem sizes without retraining. By focusing destruction on structurally critical nodes, the method drastically reduces the search space and enhances both the efficiency and solution quality of local search. Evaluated on standard CVRP benchmarks, the approach achieves state-of-the-art performance. Moreover, it successfully scales to large-scale instances with up to 30,000 customer nodes—demonstrating exceptional scalability and practical deployability in real-world logistics applications.

Technology Category

• Computer Vision: Learning & Optimization for CV
• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Graph-based Machine Learning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

In this research, we propose an iterative learning hybrid optimization solver developed to strengthen the performance of metaheuristic algorithms in solving the Capacitated Vehicle Routing Problem (CVRP). The iterative hybrid mechanism integrates the proposed Node-Destroyer Model, a machine learning hybrid model that utilized Graph Neural Networks (GNNs) such identifies and selects customer nodes to guide the Large Neighborhood Search (LNS) operator within the metaheuristic optimization frameworks. This model leverages the structural properties of the problem and solution that can be represented as a graph, to guide strategic selections concerning node removal. The proposed approach reduces operational complexity and scales down the search space involved in the optimization process. The hybrid approach is applied specifically to the CVRP and does not require retraining across problem instances of different sizes. The proposed hybrid mechanism is able to improve the performance of baseline metaheuristic algorithms. Our approach not only enhances the solution quality for standard CVRP benchmarks but also proves scalability on very large-scale instances with up to 30,000 customer nodes. Experimental evaluations on benchmark datasets show that the proposed hybrid mechanism is capable of improving different baseline algorithms, achieving better quality of solutions under similar settings.

Problem

• Enhance metaheuristic algorithms for Capacitated Vehicle Routing Problem
• Integrate Node-Destroyer Model with Large Neighborhood Search operator
• Improve solution quality and scalability for large CVRP instances

Innovation

• Hybrid Node-Destroyer Model with GNNs
• Large Neighborhood Search integration
• Scalable for large CVRP instances