Research map / Image generation / Fast diffusion sampling
Native Adaptive Solution Expansion for Diffusion-based Combinatorial Optimization
Yu Wang, Yang Li, Jiale Ma, Junchi Yan, Yi Chang
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 CO-specific one-way mask corruption instead of uniform bit-flip corruption (ablation) | NExCO · TSP-500 | gap: 0.59% -> 0.28% (5 steps) | Improved |
| use CO-specific one-way mask corruption instead of uniform bit-flip corruption (ablation) | NExCO · TSP-1000 | gap: 0.86% -> 0.63% (5 steps) | Improved |
| use native adaptive expansion instead of non-adaptive global t-schedule (ablation) | NExCO · TSP-500 | gap: 0.71% -> 0.28% (5 steps) | Improved |
| use native adaptive expansion instead of non-adaptive global t-schedule (ablation) | NExCO · TSP-1000 | gap: 0.96% -> 0.63% (5 steps) | Improved |
| use feasibility projection instead of greedy decoding with remasking (ablation) | NExCO · TSP-500 | time: 0.54s -> 0.33s at similar gap (0.31% vs 0.28%) | Improved |
| train on 2-Opt perturbed suboptimal labels (ablation) | NExCO · TSP-500 | gap: 0.25% -> 0.26% (Ds = 7) | No clear effect |
| increase expansion steps Ds from 3 to 7 (ablation) | NExCO · TSP-500 | gap: 0.39% -> 0.25% | Improved |
| set candidate threshold alpha too high or too low (ablation) | NExCO · TSP, MIS, CVRP | solution quality | Hurt |
| replace Fast T2T with NExCO as decoder | diffusion CO solver · MIS ER-[700-800] | drop vs KaMIS: 9.31% -> 4.20% | Improved |
| train on larger TSP instances before cross-scale testing (ablation) | NExCO · TSP-1000 test | gap: 3.86% -> 0.58% (train TSP-100 -> TSP-500) | Improved |
Closest papers by meaning
- COExpander: Adaptive Solution Expansion for Combinatorial Optimization (ICML 2025 · similarity 0.90)
- Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization (NeurIPS 2024 · similarity 0.90)
- A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization (ICML 2024 · similarity 0.88)
- Efficient Combinatorial Optimization via Heat Diffusion (NeurIPS 2024 · similarity 0.88)
- Search-Augmented Masked Diffusion Models for Constrained Generation (NeurIPS 2026 · similarity 0.86)
- Train for the Worst, Plan for the Best: Understanding Token Ordering in Masked Diffusions (ICML 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.
