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 2405.16409cs.AIcs.LG
收藏

神经网络中的网络拦截

Network Interdiction Goes Neural

Department of Computer Science(计算机科学系);Department of Computer Science and Engineering(计算机科学与工程系);Virginia Tech(弗吉尼亚理工学院);Mississippi State University(密苏里州立大学);Emory University(埃默里大学)

Lei Zhang, Zhiqian Chen, Chang-Tien Lu, Liang Zhao

AI总结:

本文提出利用多分区图神经网络解决双层优化的网络拦截问题,通过将问题转化为混合整数线性规划实例,提升模型泛化能力,在两个任务中优于理论基线模型和传统精确求解器。

摘要:

网络拦截问题是一种涉及两名玩家的组合优化问题:一方旨在解决网络上的优化问题,另一方则试图修改网络以阻止第一方的目标。此类问题通常出现在攻击者-防御者情境中,涵盖军事行动、疾病传播分析和通信网络管理等领域。网络拦截的主要瓶颈来自于使用传统精确求解器的高时间复杂度以及设计高效启发式求解器的挑战。GNNs作为一种前沿方法,已在图上解决单层CO问题中表现出显著效果,如旅行商问题、图匹配和图编辑距离。然而,网络拦截提出了双层优化挑战,而当前GNNs难以处理。为填补这一空白,我们将网络拦截问题表示为混合整数线性规划(MILP)实例,然后应用具有足够表示能力的多分区GNN来学习这些公式。这种方法确保我们的神经网络更兼容用于解决网络拦截问题的数学算法,从而提高泛化能力。通过两个不同的任务,我们证明了所提出的方法优于理论基线模型,并在传统精确求解器上具有优势。

英文摘要:

Network interdiction problems are combinatorial optimization problems involving two players: one aims to solve an optimization problem on a network, while the other seeks to modify the network to thwart the first player's objectives. Such problems typically emerge in an attacker-defender context, encompassing areas such as military operations, disease spread analysis, and communication network management. The primary bottleneck in network interdiction arises from the high time complexity of using conventional exact solvers and the challenges associated with devising efficient heuristic solvers. GNNs, recognized as a cutting-edge methodology, have shown significant effectiveness in addressing single-level CO problems on graphs, such as the traveling salesman problem, graph matching, and graph edit distance. Nevertheless, network interdiction presents a bi-level optimization challenge, which current GNNs find difficult to manage. To address this gap, we represent network interdiction problems as Mixed-Integer Linear Programming (MILP) instances, then apply a multipartite GNN with sufficient representational capacity to learn these formulations. This approach ensures that our neural network is more compatible with the mathematical algorithms designed to solve network interdiction problems, resulting in improved generalization. Through two distinct tasks, we demonstrate that our proposed method outperforms theoretical baseline models and provides advantages over traditional exact solvers.

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。

↑