arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.02807cs.LG
收藏

数据有限场景下面向MILP求解器的深度实例生成框架

A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability

University of Science and Technology of China(中国科学技术大学);Noah’s Ark Lab, Huawei(华为诺亚方舟实验室);Institute of Artificial Intelligence, Hefei Comprehensive National Science Center(合肥综合性国家科学中心人工智能研究院)

Zijie Geng, Xijun Li, Jie Wang, Xiao Li, Yongdong Zhang, Feng Wu

AI总结:

针对MILP求解场景下真实实例数据不足的问题,提出基于二分图表示与掩码变分自编码器的深度生成框架G2MILP,可生成兼具真实结构与计算难度的实例,助力求解器优化。

摘要:

近年来,机器学习(ML)技术被大量用于解决组合优化(CO)问题,尤其是混合整数线性规划(MILP)问题,相关应用呈爆发式增长。尽管已取得不少成果,但现实世界实例的可获取性有限,往往会导致决策次优、求解器评估存在偏差,这推动了一系列合成MILP实例生成技术的发展。然而现有方法要么严重依赖专家设计的公式,要么难以捕捉现实实例的丰富特征。\n为解决该问题,我们提出G2MILP,这是首个面向MILP实例的深度生成框架。具体而言,G2MILP将MILP实例表示为二分图,采用掩码变分自编码器迭代地对原始图的局部进行扰动与替换,从而生成新实例。G2MILP的突出优势在于,无需预先使用专家设计的公式,就能学习生成新颖且符合真实特征的MILP实例,同时保留真实数据集的结构特征与计算难度。因此生成的实例可在数据有限的场景下,为增强MILP求解器的下游任务提供支持。\n我们设计了一组基准来评估生成的MILP实例的质量。实验表明,我们的方法生成的实例在结构与计算难度两方面都与真实数据集高度相似。相关成果已发布于https://miralab-ustc.github.io/L2O-G2MILP。

英文摘要:

In the past few years, there has been an explosive surge in the use of machine learning (ML) techniques to address combinatorial optimization (CO) problems, especially mixed-integer linear programs (MILPs). Despite the achievements, the limited availability of real-world instances often leads to sub-optimal decisions and biased solver assessments, which motivates a suite of synthetic MILP instance generation techniques. However, existing methods either rely heavily on expert-designed formulations or struggle to capture the rich features of real-world instances. To tackle this problem, we propose G2MILP, the first deep generative framework for MILP instances. Specifically, G2MILP represents MILP instances as bipartite graphs, and applies a masked variational autoencoder to iteratively corrupt and replace parts of the original graphs to generate new ones. The appealing feature of G2MILP is that it can learn to generate novel and realistic MILP instances without prior expert-designed formulations, while preserving the structures and computational hardness of real-world datasets, simultaneously. Thus the generated instances can facilitate downstream tasks for enhancing MILP solvers under limited data availability. We design a suite of benchmarks to evaluate the quality of the generated MILP instances. Experiments demonstrate that our method can produce instances that closely resemble real-world datasets in terms of both structures and computational hardness. The deliverables are released at https://miralab-ustc.github.io/L2O-G2MILP.

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。

↑