mlsanityData to 7 Oct 2026

Multi-task Representation Learning for Mixed Integer Linear Programming

arXiv 2412.14409 ↗First posted 18 Dec 2024cs.AI cs.LG math.OCcited by 6

Not on the map. Why?

Abstract (arXiv)

Mixed Integer Linear Programs (MILPs) are highly flexible and powerful tools for modeling and solving complex real-world combinatorial optimization problems. Recently, machine learning (ML)-guided approaches have demonstrated significant potential in improving MILP-solving efficiency. However, these methods typically rely on separate offline data collection and training processes, which limits their scalability and adaptability. This paper introduces the first multi-task learning framework for ML-guided MILP solving. The proposed framework provides MILP embeddings helpful in guiding MILP solving across solvers (e.g., Gurobi and SCIP) and across tasks (e.g., Branching and Solver configuration). Through extensive experiments on three widely used MILP benchmarks, we demonstrate that our multi-task learning model performs similarly to specialized models within the same distribution. Moreover, it significantly outperforms them in generalization across problem sizes and tasks.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 29 of its 57 references that are in the map. First posted on arXiv 18 Dec 2024.

Builds on

29 of 57 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2021How Attentive are Graph Attention Networks?cited by 818
  4. 2023MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningcited by 617
  5. 2018End-to-End Multi-Task Learning with Attentioncited by 533
  6. 2019Exact Combinatorial Optimization with Graph Convolutional Neural Networkscited by 313
  7. 2021SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimizationcited by 229
  8. 2020Solving Mixed Integer Programs Using Neural Networkscited by 178
  9. 2019Reinforcement Learning for Integer Programming: Learning to Cutcited by 108
  10. 2022Learning To Cut By Looking Ahead: Cutting Plane Selection via Imitation Learningcited by 58
  11. 2022MIP-GNN: A Data-Driven Framework for Guiding Combinatorial Solverscited by 48
  12. 2021Learning to Schedule Heuristics in Branch-and-Boundcited by 45
17 more
  1. 2023A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programmingcited by 40
  2. 2022The Machine Learning for Combinatorial Optimization Competition (ML4CO): Results and Insightscited by 39
  3. 2024GOAL: A Generalist Combinatorial Optimization Agent Learnercited by 39
  4. 2023Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learningcited by 37
  5. 2024The SCIP Optimization Suite 9.0cited by 37
  6. 2022Learning to Compare Nodes in Branch and Bound with Graph Neural Networkscited by 30
  7. 2024Towards Foundation Models for Mixed Integer Linear Programmingcited by 30
  8. 2024Machine Learning Augmented Branch and Bound for Mixed Integer Linear Programmingcited by 24
  9. 2024Distributional MIPLIB: a Multi-Domain Library for Advancing ML-Guided MILP Methodscited by 15
  10. 2018Learning to Search via Retrospective Imitationcited by 13
  11. 2021Finding Backdoors to Integer Programs: A Monte Carlo Tree Search Frameworkcited by 12
  12. 2024Optimization Over Trained Neural Networks: Taking a Relaxing Walkcited by 10
  13. 2024CAMBranch: Contrastive Learning with Augmented MILPs for Branchingcited by 10
  14. 2023Getting Away with More Network Pruning: From Sparsity to Geometry and Linear Regionscited by 8
  15. 2021Learning Pseudo-Backdoors for Mixed Integer Programscited by 5
  16. 2022Instance-wise algorithm configuration with graph neural networkscited by 5
  17. 2023Automatic MILP Solver Configuration By Learning Problem Similaritiescited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025FORGE: Foundational Optimization Representations from Graph Embeddingscited by 2
  2. 2025ParBalans: Parallel Multi-Armed Bandits-based Adaptive Large Neighborhood Searchcited by 1
  3. 2025ID-PaS+ : Identity-Aware Predict-and-Search for General Mixed-Integer Linear Programscited by 1
  4. 2025Collab-Solver: Collaborative Solving Policy Learning for Mixed-Integer Linear Programmingcited by 0
  5. 2026Imitation Learning for Combinatorial Optimisation under Uncertaintycited by 0
  6. 2026Reformulation-Contrastive Learning for Mixed Integer Programscited by 0