Research map / Learning theory and algorithms / Combinatorial and search optimization
Towards Real-World Routing with Neural Combinatorial Optimization
Jiwoo Son, Zhikai Zhao, Federico Berto, Chuanbo Hua, Zhiguang Cao, Changhyun Kwon, Jinkyoo Park
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 |
|---|---|---|---|
| use RRNCO (ANE + NAB) instead of MatNet | node-edge NCO · ATSP in-distribution | gap (%): 3.981 -> 1.799 | Improved |
| use RRNCO instead of MatNet | node-edge NCO · ACVRP in-distribution | gap (%): 7.258 -> 3.450 | Improved |
| use RRNCO instead of node-only methods (e.g. POMO) | NCO · ACVRPTW in-distribution | gap (%): 12.559 -> 3.736 | Improved |
| add duration matrix to NAB (ablation) | RRNCO · ACVRPTW in-distribution | gap (%): 3.93 -> 3.74 | Improved |
| add angle matrix to NAB (ablation) | RRNCO · ACVRPTW in-distribution | gap (%): 4.06 -> 3.93 | Improved |
| add duration and angle in NAB (ablation) | RRNCO · ACVRPTW OOD (cluster) | gap (%): 4.84 -> 4.29 | Improved |
| train on real-world data generator instead of noise-perturbed ATSP generator (ablation) | RRNCO · ATSP in-distribution | gap (%): 7.72 -> 1.80 | Improved |
| train MatNet on real-world generator instead of ATSP generator (ablation) | MatNet · ATSP in-distribution | gap (%): 110.70 -> 3.98 | Improved |
| RRNCO instead of OR-Tools on SMTVRP | RRNCO · SMTVRP | cost / feasibility: 610.08 -> 601.03 | Improved |
Closest papers by meaning
- Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning (NeurIPS 2025 · similarity 0.92)
- SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver (NeurIPS 2026 · similarity 0.91)
- CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention (ICML 2025 · similarity 0.90)
- MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts (ICML 2024 · similarity 0.89)
- Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees (NeurIPS 2025 · similarity 0.89)
- Learning to Insert for Constructive Neural Vehicle Routing Solver (NeurIPS 2025 · similarity 0.89)
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.
