Learning Large Neighborhood Search for Maritime Inventory Routing Optimization

Maritime inventory routing optimization is an important yet challenging combinatorial optimization problem. We propose a machine learning-based local search approach for finding feasible solutions of large-scale maritime inventory routing optimization problems. Given the combinatorial complexity of the problems, we integrate a graph neural network-based neighborhood selection method to enhance local search efficiency. Our approach enables a structured exploration of different neighborhoods by imitating an optimization-based expert neighborhood selection policy, improving solution quality while maintaining computational efficiency. Through extensive computational experiments on realistic instances, we demonstrate that our method outperforms direct mixed-integer programming as well as benchmark local search approaches in solution time and solution quality.

• Publication year

  2025

• Venue

  Unknown venue

• Publication date

  2025-02-21

• Fields of study

  Mathematics, Computer Science, Engineering

• Identifiers
  arXiv 2502.15244
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Heuristic Algorithm Based on Beam Search and Iterated Local Search for the Maritime Inventory Routing Problem

  2025cited by this paper
• Machine Learning Augmented Branch and Bound for Mixed Integer Linear Programming

  2024cited by this paper
• Fifty years on maritime transportation

  2024cited by this paper
• A matheuristic for the multi-product maritime inventory routing problem

  2023cited by this paper
• An ALNS-based matheuristic algorithm for a multi-product many-to-many maritime inventory routing problem

  2023cited by this paper
• Maritime inventory routing: recent trends and future directions

  2023cited by this paper
• A Classifier to Decide on the Linearization of Mixed-Integer Quadratic Problems in CPLEX

  2022cited by this paper
• A machine learning framework for neighbor generation in metaheuristic search

  2022cited by this paper
• Maritime inventory routing with transshipment: the case of Yamal LNG

  2022cited by this paper
• An optimization approach to increasing sustainability and enhancing resilience against environmental constraints in LNG supply chains: A Qatar case study

  2022cited by this paper
• Learning to Search in Local Branching

  2022cited by this paper
• A relax-and-fix and fix-and-optimize algorithm for a Maritime Inventory Routing Problem

  2021cited by this paper
• Learning a Large Neighborhood Search Algorithm for Mixed Integer Programs

  2021cited by this paper
• End-to-End Constrained Optimization Learning: A Survey

  2021cited by this paper
• Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges

  2021cited by this paper
• Combinatorial optimization and reasoning with graph neural networks

  2021cited by this paper
• A Multi-Start Algorithm and a Large Neighborhood Search for a Maritime Inventory Routing Problem

  2020cited by this paper
• Solving Mixed Integer Programs Using Neural Networks

  2020cited by this paper
• Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning

  2020cited by this paper
• Learning chordal extensions

  2019cited by this paper
• Exact Combinatorial Optimization with Graph Convolutional Neural Networks

  2019cited by this paper
• Tailoring parallel alternating criteria search for domain specific MIPs: Application to maritime inventory routing

  2019cited by this paper
• Learning customized and optimized lists of rules with mathematical programming

  2018cited by this paper
• Recent Progress Using Matheuristics for Strategic Maritime Inventory Routing

  2018cited by this paper
• Local Search in Combinatorial Optimization

  2018cited by this paper
• Reinforcement Learning for Solving the Vehicle Routing Problem

  2018cited by this paper
• Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizon

  2018cited by this paper
• Attention, Learn to Solve Routing Problems!

  2018cited by this paper
• Learning Combinatorial Optimization Algorithms over Graphs

  2017cited by this paper
• Maritime inventory routing problem with multiple time windows

  2017cited by this paper
• Creating annual delivery programs of liquefied natural gas

  2017cited by this paper
• Sustainable maritime inventory routing problem with time window constraints

  2017cited by this paper
• Problems

  2017cited by this paper
• Representation Learning on Graphs: Methods and Applications

  2017cited by this paper
• A MIP Based Local Search Heuristic for a Stochastic Maritime Inventory Routing Problem

  2016cited by this paper
• Optimal planning of liquefied natural gas deliveries

  2016cited by this paper
• An iterative two-phase hybrid matheuristic for a multi-product short sea inventory-routing problem

  2016cited by this paper
• A hybrid heuristic strategy for liquefied natural gas inventory routing

  2015influential reference
• Two-Stage Decomposition Algorithms for Single Product Maritime Inventory Routing

  2014cited by this paper
• MIRPLib - A library of maritime inventory routing problem instances: Survey, core model, and benchmark results

  2014cited by this paper
• Hybrid heuristics for a short sea inventory routing problem

  2014cited by this paper
• Vehicle Routing Problem

  2013cited by this paper
• A maritime inventory routing problem: Practical approach

  2013cited by this paper
• Multi‐product maritime inventory routing with optional cargoes

  2013cited by this paper
• A construction and improvement heuristic for a liquefied natural gas inventory routing problem

  2012cited by this paper
• A Branch-Price-and-Cut Algorithm for Single-Product Maritime Inventory Routing

  2012cited by this paper
• A Practical Guide to Training Restricted Boltzmann Machines

  2012cited by this paper
• Large neighborhood search for LNG inventory routing

  2012influential reference
• A rolling horizon heuristic for creating a liquefied natural gas annual delivery program

  2011cited by this paper
• A Branch-and-Price Method for a Liquefied Natural Gas Inventory Routing Problem

  2010cited by this paper
• A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

  2010cited by this paper
• The Graph Neural Network Model

  2009cited by this paper
• A new model for learning in graph domains

  2005cited by this paper
• Local search heuristics for multi-index assignment problems with decomposable costs

  2004cited by this paper
• A survey of very large-scale neighborhood search techniques

  2002cited by this paper
• Marine inventory routing: shipments planning

  2002cited by this paper
• A combined ship scheduling and allocation problem

  2000cited by this paper
• Contracts

  1998cited by this paper
• Improving the Distribution of Industrial Gases with an On-Line Computerized Routing and Scheduling Optimizer

  1983cited by this paper
• A generalized assignment heuristic for vehicle routing

  1981cited by this paper
• XIII. The law of the geometric mean

  year unknowncited by this paper

• No citing papers are available for this paper.