Research map / Label-efficient and robust learning / Domain adaptation and generalization
Sym-NCO: Leveraging Symmetricity for Neural Combinatorial Optimization
Minsu Kim, Junyoung Park, 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 |
|---|---|---|---|
| add Sym-NCO symmetricity regularization to POMO (TSP, greedy) | POMO · TSP N=100 greedy | optimality gap: 1.04% -> 0.94% | Improved |
| add Sym-NCO to POMO (CVRP, greedy) | POMO · CVRP N=100 greedy | optimality gap: 3.93% -> 2.88% | Improved |
| add Sym-NCO to AM (PCTSP, greedy) | AM · PCTSP N=100 greedy | optimality gap: 4.46% -> 1.23% | Improved |
| add Sym-NCO to AM (OP, greedy) | AM · OP N=100 greedy | optimality gap: 4.75% -> 2.03% | Improved |
| add Sym-NCO to POMO on real-world TSPLIB | POMO · TSPLIB | optimality gap: 1.87% -> 1.62% | Improved |
| add invariance loss L_inv on projected representations (ablation) | Sym-NCO · TSP N=100 | cost | Improved |
| apply cosine similarity loss directly on encoder representation h instead of projected g(h) (ablation) | Sym-NCO · TSP N=100 | cost | Hurt |
| replace POMO encoder with EGNN equivariant encoder (ablation) | POMO · TSP N=100 | cost | Hurt |
| Sym-NCO multi-start vs ILS on PCTSP | AM · PCTSP N=100 multi-start | cost: 5.98 -> 5.98 | No clear effect |
Closest papers by meaning
- Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning (NeurIPS 2025 · similarity 0.89)
- Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees (NeurIPS 2025 · similarity 0.88)
- Learning Encodings for Constructive Neural Combinatorial Optimization Needs to Regret (AAAI 2024 · similarity 0.88)
- Neural Solver Selection for Combinatorial Optimization (ICML 2025 · similarity 0.88)
- Preference Optimization for Combinatorial Optimization Problems (ICML 2025 · similarity 0.88)
- Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization (ICML 2024 · similarity 0.87)
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.
