Research map / Learning theory and algorithms / Combinatorial and search optimization
Towards Efficient Constraint Handling in Neural Solvers for Routing Problems
Jieyi Bi, Zhiguang Cao, Jianan Zhou, Wen Song, Yaoxin Wu, Jie Zhang, Yining Ma, Cathy 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 |
|---|---|---|---|
| add diversification loss L_DIV (ablation) | CaR · TSPTW | optimality gap: 0.421% -> 0.014% | Improved |
| add diversification loss L_DIV (ablation) | CaR · CVRP | optimality gap: 0.325% -> 0.259% | Improved |
| add supervised loss L_SL to weak backbone (ablation) | CaR-POMO · TSPTW | optimality gap: 0.136% -> 0.014% | Improved |
| add supervised loss L_SL to strong backbone (ablation) | CaR-PIP · TSPTW | optimality gap: 0.006% -> 0.005% | No clear effect |
| add supervised loss L_SL to weak backbone (ablation) | CaR-POMO · TSPTW | infeasible ratio: 0.29% -> 0.01% | Improved |
| add shared representation (unified encoder) (ablation) | CaR · TSPTW-50 Hard | optimality gap: 0.199% -> 0.014% | Improved |
| add shared representation (unified encoder) (ablation) | CaR · TSPTW-100 Medium | optimality gap: 7.589% -> 5.815% | Improved |
| remove strict feasibility masking and use relaxed CMDP | POMO · CVRPBLTW-100 | optimality gap: 7.004% -> -1.645% | Improved |
| use R&R instead of k-opt refinement | CaR · CVRPBLTW-100 | optimality gap: -1.724% -> -2.448% | Improved |
| add CaR joint training over naive construction+improvement combination (ablation) | PIP · TSPTW-100 | optimality gap: 0.172% -> 0.146% | Improved |
| train CaR on loose constraints instead of PIP on tight, test on tight | CaR-PIP · TSPTW-100 Hard | infeasible ratio: 4.62% -> 3.52% | Improved |
| add CaR refinement to PIP in cross-scale generalization | CaR · CVRPBLTW-200 | optimality gap: 4.51% -> 2.09% | Improved |
Closest papers by meaning
- Learning to Handle Complex Constraints for Vehicle Routing Problems (NeurIPS 2024 · similarity 0.88)
- Memory-Enhanced Neural Solvers for Routing Problems (NeurIPS 2025 · similarity 0.87)
- SPACE: Unifying Symmetric and Asymmetric Routing Problems for Generalist Neural Solver (NeurIPS 2026 · similarity 0.87)
- LINC: Decoupling Local Consequence Scoring from Hidden Matching in Constructive Neural Routing (NeurIPS 2026 · similarity 0.87)
- CaDA: Cross-Problem Routing Solver with Constraint-Aware Dual-Attention (ICML 2025 · similarity 0.86)
- Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees (NeurIPS 2025 · similarity 0.86)
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.
