Research map / Learning theory and algorithms / Combinatorial and search optimization
A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability
Zijie Geng, Xijun Li, Jie Wang, Xiao Li, Yongdong Zhang, Feng Wu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace G2MILP decoder networks with random generators (Random) (ablation) | G2MILP · MIS | structural similarity score: 0.997 vs 0.651 | Hurt |
| increase masking ratio from 0.01 to 0.1 (ablation) | G2MILP · MIS | structural similarity score: 0.997 -> 0.895 | Hurt |
| increase masking ratio from 0.01 to 0.1 (ablation) | G2MILP · MIK | structural similarity score: 0.991 -> 0.918 | Hurt |
| increase masking ratio from 0.01 to 0.1 (ablation) | G2MILP · MIS | Gurobi solving time (s): 0.354 -> 0.214 | Hurt |
| increase masking ratio from 0.01 to 0.1 (ablation) | G2MILP · MIK | Gurobi solving time (s): 0.169 -> 0.072 | Hurt |
| increase masking ratio from 0.01 to 0.1 (ablation) | G2MILP · MIS | average branching nodes: 15.03 -> 4.61 | Hurt |
| replace Random with G2MILP at eta=0.1 (ablation) | Random generator · MIS | average branching nodes: 484.47 -> 4.61 | Improved |
| augment training data with G2MILP instances (ablation) | GNN value predictor · MIK | MSE: 0.0236 -> 0.0073 | Improved |
| augment training data with Random instances (ablation) | GNN value predictor · MIK | MSE: 0.0236 -> 0.0104 | Improved |
| augment training data with G2MILP instances (ablation) | GNN value predictor · Nurse Scheduling | MSE: 679.75 -> 548.70 | Improved |
| augment training data with Bowly instances (ablation) | GNN value predictor · Nurse Scheduling | MSE: 679.75 -> 663.52 | No clear effect |
| augment predict-and-search training data with G2MILP instances (ablation) | predict-and-search · MIS | Gurobi time: 0.041 -> 0.032 | Improved |
Closest papers by meaning
- MILP-StuDio: MILP Instance Generation via Block Structure Decomposition (NeurIPS 2024 · similarity 0.91)
- MILP-FBGen: LP/MILP Instance Generation with Feasibility/Boundedness (ICML 2024 · similarity 0.90)
- ACM-MILP: Adaptive Constraint Modification via Grouping and Selection for Hardness-Preserving MILP Instance Generation (ICML 2024 · similarity 0.88)
- Towards Foundation Models for Mixed Integer Linear Programming (ICLR 2025 · similarity 0.87)
- RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains (NeurIPS 2025 · similarity 0.86)
- Predicting Lagrangian Multipliers for Mixed Integer Linear Programs (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
