mlsanityData to 14 Oct 2026

MILP-StuDio: MILP Instance Generation via Block Structure Decomposition

arXiv 2410.22806 ↗First posted 30 Oct 2024cs.LG cs.DMcited by 17

Not on the map. Why?

Abstract (arXiv)

Mixed-integer linear programming (MILP) is one of the most popular mathematical formulations with numerous applications. In practice, improving the performance of MILP solvers often requires a large amount of high-quality data, which can be challenging to collect. Researchers thus turn to generation techniques to generate additional MILP instances. However, existing approaches do not take into account specific block structures -- which are closely related to the problem formulations -- in the constraint coefficient matrices (CCMs) of MILPs. Consequently, they are prone to generate computationally trivial or infeasible instances due to the disruptions of block structures and thus problem formulations. To address this challenge, we propose a novel MILP generation framework, called Block Structure Decomposition (MILP-StuDio), to generate high-quality instances by preserving the block structures. Specifically, MILP-StuDio begins by identifying the blocks in CCMs and decomposing the instances into block units, which serve as the building blocks of MILP instances. We then design three operators to construct new instances by removing, substituting, and appending block units in the original instances, enabling us to generate instances with flexible sizes. An appealing feature of MILP-StuDio is its strong ability to preserve the feasibility and computational hardness of the generated instances. Experiments on the commonly-used benchmarks demonstrate that using instances generated by MILP-StuDio is able to significantly reduce over 10% of the solving time for learning-based solvers.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 18 of its 60 references that are in the map. First posted on arXiv 30 Oct 2024.

Builds on

18 of 60 references.

References · 18

  1. 2013Auto-Encoding Variational Bayescited by 4,053
  2. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 318
  3. 2020Solving Mixed Integer Programs Using Neural Networkscited by 182
  4. 2019Reinforcement Learning for Integer Programming: Learning to Cutcited by 111
  5. 2020Hybrid Models for Learning to Branchcited by 95
  6. 2023Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Modelcited by 45
  7. 2020Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solverscited by 43
  8. 2021Learning a Large Neighborhood Search Algorithm for Mixed Integer Programscited by 43
  9. 2023A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programmingcited by 41
  10. 2022The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insightscited by 39
  11. 2023Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learningcited by 37
  12. 2022Learning to Compare Nodes in Branch and Bound with Graph Neural Networkscited by 31
6 more
  1. 2022Lookback for Learning to Branchcited by 27
  2. 2023A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availabilitycited by 21
  3. 2019G2SAT: Learning to Generate SAT Formulascited by 20
  4. 2024CAMBranch: Contrastive Learning with Augmented MILPs for Branchingcited by 10
  5. 2023Accelerate Presolve in Large-Scale Linear Programming via Reinforcement Learningcited by 7
  6. 2024Machine Learning Insides OptVerse AI Solver: Design Principles and Applicationscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 4.

17 papers.

Sort:

By area:

  1. 2025OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modelingcited by 49
  2. 2025Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programmingcited by 16
  3. 2025Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Trainingcited by 14
  4. 2025Distinguished Quantized Guidance for Diffusion-based Sequence Recommendationcited by 13
  5. 2025SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioningcited by 5
  6. 2025CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Predictioncited by 4
  7. 2025Accurate and Scalable Graph Neural Networks via Message Invariancecited by 3
  8. 2025On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenderscited by 3
  9. 2025STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problemcited by 3
  10. 2025RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domainscited by 3
  11. 2025Are Your Generated Instances Truly Useful? GenBench-MILP: A Benchmark Suite for MILP Instance Generationcited by 2
  12. 2025Principled Data Augmentation for Learning to Solve Quadratic Programming Problemscited by 2
5 more
  1. 2025Code Retrieval for MILP Instance Generationcited by 1
  2. 2026EvoOptiGraph: Weakness-Driven Coevolution via Graph-Based Structural Generation for Optimization Modelingcited by 0
  3. 2026GraphBU: MILP Instance Generation with Graph-Native Block Unitscited by 0
  4. 2026MGDiff: Multi-Interest Sequence Recommendation with Masking GNN-Guided Diffusioncited by 0
  5. 2026Teaching LLMs to Generate Challenging MILP Instances via Solver Feedbackcited by 0