Research map / Graph learning / Graph algorithms and clustering
Graph Learning Assisted Multi-Objective Integer Programming
Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang, Abhishek Gupta, Mingyan Simon Lin
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 |
|---|---|---|---|
| add learned GNN reduction rule | ODA-T · MOKP(3-100) | runtime (s): 993.3 -> 486.9 | Improved |
| add learned GNN reduction rule | ODA-T · MOKP(4-100) | cardinality: 3691.4 -> 4000.7 | Improved |
| add learned GNN reduction rule | ODA-T · MOAP(3-50) | cardinality: 2532.9 -> 3564.4 | Improved |
| add learned GNN reduction rule | ODA-T · MOAP(4-50) | HV: 0.52 -> 0.67 | Improved |
| add learned GNN reduction rule | ODA-T · MOAP(4-50) | IGD: 0.017 -> 0.011 | Improved |
| add learned GNN reduction rule | ODA-T · MOKP(3-100) | cardinality: 4169.8 -> 3379.7 | Hurt |
| add learned reduction rule, generalize to larger size | ODA-T · MOKP(4-150) | cardinality: 3649.7 -> 4032.6 | Improved |
| add learned reduction rule, generalize to 5 objectives | ODA-T · MOKP(5-100) | HV: 0.66 -> 0.66 | No clear effect |
| add learned reduction rule, generalize to 5 objectives | ODA-T · MOAP(5-50) | cardinality: 2511.8 -> 3089.2 | Improved |
| add second-stage hypernode aggregation to GIN (ablation) | GIN · MOKP(3-100) test | accuracy: 79.7 -> 80.7 | Improved |
| add second-stage hypernode aggregation to GIN (ablation) | GIN · MOKP(4-150) generalization | accuracy: 59.5 -> 59.5 | No clear effect |
| replace GIN by proposed first-stage attention GNN (ablation) | 2-stage GIN · MOKP(5-100) generalization | accuracy: 58.8 -> 73.9 | Improved |
Closest papers by meaning
- Expressive Power of Graph Neural Networks for (Mixed-Integer) Quadratic Programs (ICML 2025 · similarity 0.87)
- BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks (NeurIPS 2025 · similarity 0.86)
- On the Power of Small-size Graph Neural Networks for Linear Programming (NeurIPS 2024 · similarity 0.85)
- Generalization Guarantees for Learning Score-Based Branch-and-Cut Policies in Integer Programming (NeurIPS 2025 · similarity 0.85)
- Learning Initial Basis Selection for Linear Programming via Duality-Inspired Tripartite Graph Representation and Comprehensive Supervision (ICML 2025 · similarity 0.84)
- Apollo-MILP: An Alternating Prediction-Correction Neural Solving Framework for Mixed-Integer Linear Programming (ICLR 2025 · 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.
