Research map / Learning theory and algorithms / Combinatorial and search optimization
UniCO: On Unified Combinatorial Optimization via Problem Reduction to Matrix-Encoded General TSP
Wenzheng Pan, Hao Xiong, Jiale Ma, Wentao Zhao, Yang Li, Junchi Yan
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes UniCO, which reduces diverse combinatorial optimization problems to a general matrix-encoded TSP form so a single neural solver can handle them.
Problem
Neural solvers for combinatorial optimization are usually tailored to specific problem types (TSP, CVRP, SAT, etc.), and it is unclear how to achieve universal problem representation and learning within one framework.
Approach
Reduce a set of CO problems into a general TSP form encoded by a distance matrix, so that one unified neural solver can learn across problem types instead of per-problem architectures.
Closest papers by meaning
- ASP: Learn a Universal Neural Solver! (TPAMI 2024 · similarity 0.89)
- Neural Solver Selection for Combinatorial Optimization (ICML 2025 · similarity 0.88)
- GOAL: A Generalist Combinatorial Optimization Agent Learner (ICLR 2025 · similarity 0.87)
- PolyNet: Learning Diverse Solution Strategies for Neural Combinatorial Optimization (ICLR 2025 · similarity 0.87)
- UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems (NeurIPS 2024 · similarity 0.86)
- Fast T2T: Optimization Consistency Speeds Up Diffusion-Based Training-to-Testing Solving for Combinatorial Optimization (NeurIPS 2024 · 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.
