Research map / Graph learning / Graph algorithms and clustering
GNN&GBDT-Guided Fast Optimizing Framework for Large-scale Integer Programming
Huigen Ye, Hua Xu, Hongyan Wang, Chengming Wang, Yu Jiang
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 |
|---|---|---|---|
| Small-scale SCIP with 20% variable proportion inside the framework vs. full-scale SCIP | SCIP as large-scale baseline · Benchmark IPs, same wall-clock time (Table 1) | objective value | Improved |
| Small-scale SCIP/Gurobi at 30% variable proportion inside the framework | SCIP and Gurobi · Benchmark IPs, same wall-clock time (Table 1) | objective value | Improved |
| Variable proportion increased from 30% to 50% (ablation) | framework with small-scale optimizer · Benchmark IPs, same wall-clock time (Table 1) | objective value | Mixed |
| Small-scale SCIP inside the framework vs. Gurobi full-scale | SCIP as small-scale optimizer · Benchmark IPs, same wall-clock time | objective value | Improved |
| Framework with 30%-size small optimizer vs. same optimizer at full scale, time to reach same objective | SCIP and Gurobi on MIS2 and MVC2 · Table 2 running time | running time: SCIP baseline >20000s vs 969.8s (MIS2) ; Gurobi baseline >20000s vs 1121.8s-level framework | Improved |
Closest papers by meaning
- On the Power of Small-size Graph Neural Networks for Linear Programming (NeurIPS 2024 · similarity 0.86)
- Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs (ICML 2025 · similarity 0.86)
- DOGE-Train: Discrete Optimization on GPU with End-to-End Training (AAAI 2024 · similarity 0.85)
- BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks (NeurIPS 2025 · similarity 0.85)
- Large Language Model-driven Large Neighborhood Search for Large-Scale MILP Problems (ICML 2025 · similarity 0.84)
- Rethinking the Capacity of Graph Neural Networks for Branching Strategy (NeurIPS 2024 · similarity 0.84)
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.
