RLR:一种基于资源负荷率的链路预测算法  

RLR:a Link Prediction Algorithm Based on Resource Load Ratio

作　　者：聂聆聪 王剑[1,2] 刘前[3] 张岳松 宁俊 刘昱岑 NIE Lingcong;WANG Jian;LIU Qian;ZHANG Yuesong;NING Jun;LIU Yucen(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China;Yunnan Key Laboratory of Artificial Intelligence,Kunming University of Science and Technology,Kunming 650500,China;School of Software,Yunnan University,Kunming 650091,China;College of Land Resources and Engineering,Kunming University of Science and Technology,Kunming 650093,China)

机构地区：[1]昆明理工大学信息工程与自动化学院,昆明650500 [2]昆明理工大学云南省人工智能重点实验室,昆明650500 [3]云南大学软件学院,昆明650091 [4]昆明理工大学国土资源与工程学院,昆明650093

出　　处：《小型微型计算机系统》2024年第11期2761-2767,共7页Journal of Chinese Computer Systems

基　　金：国家自然科学基金项目(62066048)资助;国家国防科工局高分辨率对地观测系统重大专项项目(89-Y50G31-9001-22/23)资助;云南省重大科技计划专项计划项目(202102AA100021)资助;云南省自然科学基金项目(202101AT070167)资助.

摘　　要：近年来,复杂网络得到了广泛的研究,链路预测作为复杂网络研究的一个重要分支,其本质是根据已观测到的信息预测网络中缺失的链路或未来可能出现的链路.解决链路预测问题的关键是如何高效地计算网络中节点之间的相似度,研究者们提出了许多基于节点相似性的链路预测算法,但算法准确性仍有待提高.本文提出一种基于资源负荷率(Resource Load Ratio)的链路预测算法.首先,根据节点拓扑属性与网络全局属性的占比量化节点资源储备,并将资源储备作为衡量节点重要性的主要因素.其次,根据两个节点的共同邻居数量与所有邻居数量占比量化节点间密集度,并上升到二阶节点.最后,基于节点间资源储备和密集度提出相应的链路预测算法.在8个真实网络上的实验结果表明,该算法在准确性和鲁棒性方面均取得了最优.In recent years,complex networks have been widely studied,and link prediction,as an important branch of complex network research,is essentially predicting the missing links in the network or the links that may appear in the future based on the observed information.The key to solving the link prediction problem is how to efficiently calculate the similarity between nodes in the network,and researchers have proposed many link prediction algorithms based on node similarity,but the accuracy of the algorithm still needs to be improved.This paper proposes a link prediction algorithm based on Resource Load Ratio.Firstly,the node resource reserve is quantified according to the proportion of node topology attributes and global network attributes,and the resource reserve is used as the main factor to measure the importance of nodes.Secondly,the node density is quantified according to the proportion of the number of common neighbors and the number of all neighbors of the two nodes,and rises to the second-order node.Finally,based on the resource reserve and density between nodes,the corresponding link prediction algorithm is proposed.Experimental results on eight real networks show that the algorithm achieves the best in terms of accuracy and robustness.

关 键 词：复杂网络 链路预测 资源储备 密集度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]