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 2501.14211cs.LGmath.OC
收藏

当 GNN 遇上 ILP 中的对称性:一种基于轨道的特征增强方法

When GNNs meet symmetry in ILPs: an orbit-based feature augmentation approach

School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)理工学院);Shenzhen International Center for Industrial and Applied Mathematics(深圳国际工业与应用数学中心);Shenzhen Research Institute of Big Data(深圳大数据研究院);School of Data Science, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)数据科学学院);School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)人工智能学院);School of Software Engineering, Tongji University, Shanghai(同济大学软件学院)

Qian Chen, Lei Li, Qian Li, Jianghua Wu, Akang Wang, Ruoyu Sun, Xiaodong Luo, Tsung-Hui Chang, Qingjiang Shi

AI总结:

针对 GNN 难以区分对称 ILP 变量的问题,本文分析置换等变性与不变性,并提出基于轨道分组和离散均匀采样的特征增强方法,显著提升训练效率与预测性能。

摘要:

整数线性规划(ILP)的一个共同特征是对称性,即变量可以在不改变底层问题结构的情况下进行置换。近年来,图神经网络(GNN)已成为求解 ILP 的一种有前景的方法。然而,将 GNN 应用于具有对称性的 ILP 时会出现一个重大挑战:经典 GNN 架构难以区分对称变量,这限制了它们的预测精度。在本工作中,我们研究了 GNN 中置换等变性和不变性的性质,尤其是其与 ILP 表述固有对称性之间的关系。我们揭示,这两个因素之间的相互作用导致了区分对称变量的困难。为应对这一挑战,我们探索了特征增强的潜力,并提出了若干构建增强特征的指导原则。基于这些原则,我们开发了一种基于轨道的增强方案:首先对对称变量进行分组,然后针对每个组从离散均匀分布中采样增强特征。实证结果表明,我们提出的方法显著提升了训练效率和预测性能。

英文摘要:

A common characteristic in integer linear programs (ILPs) is symmetry, allowing variables to be permuted without altering the underlying problem structure. Recently, GNNs have emerged as a promising approach for solving ILPs. However, a significant challenge arises when applying GNNs to ILPs with symmetry: classic GNN architectures struggle to differentiate between symmetric variables, which limits their predictive accuracy. In this work, we investigate the properties of permutation equivariance and invariance in GNNs, particularly in relation to the inherent symmetry of ILP formulations. We reveal that the interaction between these two factors contributes to the difficulty of distinguishing between symmetric variables. To address this challenge, we explore the potential of feature augmentation and propose several guiding principles for constructing augmented features. Building on these principles, we develop an orbit-based augmentation scheme that first groups symmetric variables and then samples augmented features for each group from a discrete uniform distribution. Empirical results demonstrate that our proposed approach significantly enhances both training efficiency and predictive performance.

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。

↑