mlsanityData to 14 Oct 2026

A General Neural Backbone for Mixed-Integer Linear Optimization via Dual Attention

arXiv 2601.04509 ↗First posted 8 Jan 2026cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

Mixed-integer linear programming (MILP) is a foundational framework for combinatorial optimization across science and engineering, but remains hard to solve at scale due to NP-hardness. Recent learning-based methods typically model MILP instances as variable-constraint bipartite graphs and use Graph Neural Networks (GNNs) for representation learning, yet their locality limits representation power. We propose an attention-driven neural backbone that adopts an element-centric view of variables and constraints, with dual attention performing parallel intra-type self-attention and inter-type cross-attention. Across three representative tasks at the instance, element, and solving-state levels, our model consistently outperforms conventional GNN-based architectures, highlighting attention-based, element-centric modeling as a powerful foundation for learning-enhanced combinatorial optimization.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 36 of its 63 references that are in the map. First posted on arXiv 8 Jan 2026.

Builds on

36 of 63 references.

References · 36

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
  3. 2021How Attentive are Graph Attention Networks?cited by 835
  4. 2018Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizoncited by 623
  5. 2021Understanding over-squashing and bottlenecks on graphs via curvaturecited by 478
  6. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 318
  7. 2021Combinatorial optimization and reasoning with graph neural networkscited by 268
  8. 2019Reinforcement Learning for Integer Programming: Learning to Cutcited by 111
  9. 2020Hybrid Models for Learning to Branchcited by 95
  10. 2024Polynormer: Polynomial-Expressive Graph Transformer in Linear Timecited by 65
  11. 2020Parameterizing Branch-and-Bound Search Trees to Learn Branching Policiescited by 63
  12. 2022Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learningcited by 61
24 more
  1. 2022MIP-GNN: A Data-Driven Framework for Guiding Combinatorial Solverscited by 49
  2. 2022Learning to branch with Tree MDPscited by 45
  3. 2020Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solverscited by 43
  4. 2025On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learningcited by 43
  5. 2023A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programmingcited by 41
  6. 2022The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insightscited by 39
  7. 2023Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learningcited by 37
  8. 2024The SCIP Optimization Suite 9.0cited by 37
  9. 2021Learning Large Neighborhood Search Policy for Integer Programmingcited by 35
  10. 2021Mixed-Integer Optimization with Constraint Learningcited by 31
  11. 2024Towards Foundation Models for Mixed Integer Linear Programmingcited by 31
  12. 2022Lookback for Learning to Branchcited by 27
  13. 2024Machine Learning Augmented Branch and Bound for Mixed Integer Linear Programmingcited by 24
  14. 2022On Representing Mixed-Integer Linear Programs by Graph Neural Networkscited by 23
  15. 2024Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programscited by 16
  16. 2025Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programmingcited by 16
  17. 2024Rethinking the Capacity of Graph Neural Networks for Branching Strategycited by 12
  18. 2024Learning to Cut via Hierarchical Sequence/Set Model for Efficient Mixed-Integer Programmingcited by 12
  19. 2023Mixed-Integer Optimisation of Graph Neural Networks for Computer-Aided Molecular Designcited by 9
  20. 2024Towards a General Recipe for Combinatorial Optimization with Multi-Filter GNNscited by 9
  21. 2024SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branchcited by 9
  22. 2024Learning to Stop Cut Generation for Efficient Mixed-Integer Linear Programmingcited by 8
  23. 2024Learning to Remove Cuts in Integer Linear Programmingcited by 4
  24. 2019Computation of systemic risk measures: a mixed-integer programming approachcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Solving Integer Linear Programming with Parallel Temperingcited by 0