# Thinklab-SJTU/awesome-ml4co

Awesome machine learning for combinatorial optimization papers.

Repository: https://github.com/Thinklab-SJTU/awesome-ml4co
Canonical: https://ross.abutalabs.com/products/awesome-ml4co
Language: Python
License Family: other
Topics: machine-learning, combinatorial-optimization, operations-research, paper-list
Last push: 2026-07-19T06:46:19+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 35, longevity 100
- inputs: {"age_days": 1991, "days_push": 45, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2164, forks 241 (observed 2026-08-28T04:06:21.225306+00:00)

## What it is
A curated awesome-list of research papers applying machine learning to combinatorial optimization problems such as TSP, graph matching, scheduling, and SAT. It is maintained by SJTU Thinklab and organized by problem domain with survey sections.

## Use cases
- find papers on machine learning for combinatorial optimization
- survey neural approaches to the travelling salesman problem
- research learning-based solvers for graph matching
- keep up with ML for operations research literature
- find reinforcement learning methods for job shop scheduling
- start studying neural combinatorial optimization

## When to choose
- you need a curated, categorized reading list of ML4CO papers
- you are a researcher surveying learning-based optimization methods
- you want community-maintained coverage of a specific problem like TSP or MIP

## When to avoid
- you need runnable solver code rather than a paper index
- you want a library or tool to integrate into your project
- you need non-optimization machine learning resources

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, developer-tools
- domain: machine-learning, tutorials, awesome-lists
- platform: cross-platform
- tags: awesome-list, combinatorial-optimization, operations-research, paper-list, reinforcement-learning, graph-neural-networks, algorithms

## Member repositories
- Thinklab-SJTU/awesome-ml4co (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:21.225306+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:50:00.287667+00:00, confidence not recorded.
  - readme: https://github.com/Thinklab-SJTU/awesome-ml4co (fetched 2026-08-28T04:06:21.225306+00:00, sha 2d05fca4e027)
- Data as of 2026-08-30T08:39:29.467469+00:00.