<2-3 sentences summarising what the project addresses and solves, the target audience, and the benefit.> This repository is a comprehensive, curated collection of academic papers focused on applying machine learning techniques to solve combinatorial optimization problems. It targets researchers, engineers, and practitioners seeking to leverage ML for complex optimization challenges, providing a structured overview of the state-of-the-art and a valuable resource for identifying relevant research.

How It Works

The project functions as an extensive bibliography, meticulously categorizing research papers by specific combinatorial optimization problems such as Job Shop Scheduling (JSSP), Traveling Salesman Problem (TSP), Vehicle Routing Problem (VRP), Knapsack, and Boolean Satisfiability (SAT), among many others. It also includes dedicated sections for survey papers. This structured approach allows users to quickly navigate and discover relevant ML methodologies and applications within their areas of interest.

Quick Start & Requirements

N/A (This is a curated list of research papers, not a software project with installation or execution requirements.)

Highlighted Details

• Extensive coverage of numerous combinatorial optimization problems, from classic NP-hard problems to specialized areas like Electronic Design Automation (EDA) and Causal Discovery.
• Inclusion of survey papers offering broad overviews of ML for combinatorial optimization.
• Many listed papers indicate associated code implementations (marked with ⭐ and "code"), facilitating reproducibility and practical application.
• Maintained by SJTU-Thinklab, with active recruitment for post-doctoral researchers in the field.

Maintenance & Community

The repository is actively maintained by members of SJTU-Thinklab. The maintainers are also seeking post-doctoral researchers, indicating ongoing research engagement and community involvement.

Licensing & Compatibility

No specific licensing information is provided in the README. Users should verify licensing for any associated code or research derived from this list.

Limitations & Caveats

This resource is a curated list of papers and does not provide a ready-to-use software framework or tools. Users must independently access, implement, and evaluate the research papers. The absence of explicit licensing details for the listed resources is a notable caveat.