arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2406.02872cs.LGcs.AI
收藏

基于自动化图神经网络的组合优化

Combinatorial Optimization with Automated Graph Neural Networks

Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院);Hangzhou Yugu Technology Co., Ltd(杭州宇谷科技有限公司);Zhejiang University(浙江大学);Guangzhou University(广州大学);Zhejiang Lab(之江实验室)

Yang Liu, Peng Zhang, Yang Gao, Chuan Zhou, Zhao Li, Hongyang Chen

AI总结:

本文提出AutoGNP,通过图神经架构搜索自动设计用于求解混合整数线性规划和二次无约束二值优化等NP难组合优化问题的GNN,并利用两跳算子、模拟退火和严格早停策略避免局部最优,在基准问题上表现优越。

摘要:

近年来,图神经网络(GNNs)在求解NP难组合优化(CO)问题(如最大割和最大独立集)方面日益受到关注。这些方法的核心思想是将组合优化问题表示为图,然后利用GNNs学习带有组合信息的节点/图嵌入。尽管这些方法已取得有前景的结果,但针对特定组合优化问题,GNN架构的设计仍需要大量依赖领域知识的人工工作。现有的自动化GNN大多集中于传统图学习问题,不适用于求解NP难组合优化问题。为此,我们提出了一类新的用于求解NP难问题的自动化GNN,即AutoGNP。我们用GNN表示组合优化问题,并聚焦于两个具体问题,即混合整数线性规划和二次无约束二值优化。AutoGNP的思想是利用图神经架构搜索算法自动为给定的NP难组合优化问题寻找最佳GNN。与现有的图神经架构搜索算法相比,AutoGNP在架构搜索空间中利用了两跳算子。此外,AutoGNP利用模拟退火和严格的早停策略来避免局部最优解。在基准组合问题上的实验结果表明了我们所提模型的优越性。

英文摘要:

In recent years, graph neural networks (GNNs) have become increasingly popular for solving NP-hard combinatorial optimization (CO) problems, such as maximum cut and maximum independent set. The core idea behind these methods is to represent a CO problem as a graph and then use GNNs to learn the node/graph embedding with combinatorial information. Although these methods have achieved promising results, given a specific CO problem, the design of GNN architectures still requires heavy manual work with domain knowledge. Existing automated GNNs are mostly focused on traditional graph learning problems, which is inapplicable to solving NP-hard CO problems. To this end, we present a new class of \textbf{AUTO}mated \textbf{G}NNs for solving \textbf{NP}-hard problems, namely \textbf{AutoGNP}. We represent CO problems by GNNs and focus on two specific problems, i.e., mixed integer linear programming and quadratic unconstrained binary optimization. The idea of AutoGNP is to use graph neural architecture search algorithms to automatically find the best GNNs for a given NP-hard combinatorial optimization problem. Compared with existing graph neural architecture search algorithms, AutoGNP utilizes two-hop operators in the architecture search space. Moreover, AutoGNP utilizes simulated annealing and a strict early stopping policy to avoid local optimal solutions. Empirical results on benchmark combinatorial problems demonstrate the superiority of our proposed model.

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。

↑