CoCo-MILP:变量间对比与约束内竞争的混合整数线性规划解预测
CoCo-MILP: Inter-Variable Contrastive and Intra-Constraint Competitive MILP Solution Prediction
AI总结:
针对现有方法与MILP内在结构的不一致问题,提出CoCo-MILP,通过变量间对比损失和约束内竞争GNN层建模变量优先级与约束内竞争关系,在标准基准上解差距最多减少68.12%,显著优于现有方法。
摘要:
混合整数线性规划(MILP)是组合优化的基石,但求解大规模实例仍面临重大计算挑战。近年来,图神经网络(GNN)在通过预测高质量解加速MILP求解器方面展现出潜力。然而,我们发现现有方法在两个层面上与MILP问题的内在结构不一致:在学习目标层面,二元交叉熵(BCE)损失独立处理变量,忽略了它们的相对优先级,导致生成看似合理的对数概率;在模型架构层面,标准GNN消息传递本质上会平滑变量间的表示,未能捕捉约束内的自然竞争关系。为解决这些挑战,我们提出CoCo-MILP,它明确建模变量间对比和约束内竞争以实现先进的MILP解预测。在目标层面,CoCo-MILP引入变量间对比损失(VCL),明确最大化被分配1和0的变量之间的嵌入差距;在架构层面,我们设计约束内竞争GNN层,该层不同质化特征,而是学习区分约束内竞争变量的表示,捕捉它们的互斥性。在标准基准上的实验结果表明,CoCo-MILP显著优于现有基于学习的方法,与传统求解器相比,解差距最多减少68.12%。我们的代码可在https://github.com/happypu326/CoCo-MILP获取。
英文摘要:
Mixed-Integer Linear Programming (MILP) is a cornerstone of combinatorial optimization, yet solving large-scale instances remains a significant computational challenge. Recently, Graph Neural Networks (GNNs) have shown promise in accelerating MILP solvers by predicting high-quality solutions. However, we identify that existing methods misalign with the intrinsic structure of MILP problems at two levels. At the leaning objective level, the Binary Cross-Entropy (BCE) loss treats variables independently, neglecting their relative priority and yielding plausible logits. At the model architecture level, standard GNN message passing inherently smooths the representations across variables, missing the natural competitive relationships within constraints. To address these challenges, we propose CoCo-MILP, which explicitly models inter-variable Contrast and intra-constraint Competition for advanced MILP solution prediction. At the objective level, CoCo-MILP introduces the Inter-Variable Contrastive Loss (VCL), which explicitly maximizes the embedding margin between variables assigned one versus zero. At the architectural level, we design an Intra-Constraint Competitive GNN layer that, instead of homogenizing features, learns to differentiate representations of competing variables within a constraint, capturing their exclusionary nature. Experimental results on standard benchmarks demonstrate that CoCo-MILP significantly outperforms existing learning-based approaches, reducing the solution gap by up to 68.12% compared to traditional solvers. Our code is available at https://github.com/happypu326/CoCo-MILP.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。