[
    {
        "id": "osp-21342",
        "type": "article-journal",
        "title": "Reformulation-Contrastive Learning for Mixed Integer Programs",
        "author": [
            {
                "family": "Bouaneni",
                "given": "Ousema"
            },
            {
                "family": "Bail",
                "given": "Mathis Le"
            },
            {
                "family": "Elliker",
                "given": "Clément"
            },
            {
                "family": "Jenny",
                "given": "Maël"
            },
            {
                "family": "Vanier",
                "given": "Sonia"
            }
        ],
        "URL": "https://omanscience.com/en/articles/reformulation-contrastive-learning-for-mixed-integer-programs",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Mixed-integer linear programs (MILP) model many real-world decision problems, motivating machine-learning methods that exploit recurring structure to accelerate MILP solving. MILPs can admit many equivalent formulations: integrality-preserving changes of variables and the addition of redundant constraints can alter their formulations while preserving the optimization problem. We leverage these reformulations as a source of self-supervision for learning general-purpose representations of MILP variables and constraints. We characterize the affine reformulations that are valid for every input instance, and distinguish re-descriptions, which leave variables unchanged, from substitutions, which transform them predictably. Building on equivariant self-supervised learning, we introduce ReMILP (reformulation-contrastive MILP representation learning), which jointly trains a graph neural network and a hypernetwork to predict how variable embeddings transform under changes of variables. Without solver-derived labels, ReMILP learns representations that exhibit the intended invariance and equivariance on unseen problem classes. Across binary solution, constraint activity and integrality gap prediction, these representations carry task-relevant information when frozen and provide a useful initialization for fine-tuning."
    }
]