ConRep4CO

[ICLR 2026] ConRep4CO: Contrastive Representation Learning of Combinatorial Optimization Instances across Types

Installation

You can run the following commands to get started:

conda create -n newenv python=3.9
conda activate newenv
bash scripts/install.sh

To generate our used datasets, you can refer to the following scripts:

# generate datasets
bash scripts/gen_data.sh

To train the graph and SAT models, you can refer to the following scripts:

# train models
bash scripts/run_training.sh

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
g4satbench		g4satbench
scripts		scripts
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
eval_model.py		eval_model.py
requirements.txt		requirements.txt
setup.py		setup.py
train_model.py		train_model.py