基于概率矩阵分解的个性化链接预测算法

链接预测是社会网络分析中一个具有挑战性的问题。社会网络中的链接预测问题就是预测社会实体间未被发现的链接和即将演化产生的链接。已有的链接预测算法大多基于社会网络本身的拓扑结构,而忽视社会实体自身的个性化特征。针对以上问题,结合社会实体的个性化特征和社会网络的拓扑特征,提出一种基于概率矩阵分解模型的个性化链接预测算法。该算法整合了社会网络的拓扑特征和实体的个性化信息,建立概率矩阵分解模型,并通过基于梯度的优化算法对模型进行求解。在两个数据集上进行多组实验,一个是数据挖掘领域的合作者网络,另一个是电子商务消费者的信任网络。实验结果证明该算法较现有方法预测准确率有了较大提高。     

基于元路径与节点属性的合著关系预测

在异构社会网络中,合著关系的预测是具有代表性的一类关系预测,与同构网络的链接预测方法在节点表示、网络构造等方面存在较大差异。综合考虑异构社会网络特有的元路径信息和节点属性特征,提出了节点的复合向量化表示：将节点的TF-IDF特征与基于Metapath2vec算法的向量化表示相结合;在元路径的表示上采取元路径中同类型节点归并重构的方法,以提取元路径中同类型节点间的隐含信息;并通过卷积神经网络（CNN）实现学术网络的合著关系预测。实验结果表明,节点的复合向量化表示及重构元路径方法可以更好地表征异构社会网络,与其他方法对比中均获得更好的预测评价指标。     

融合多元影响力节点识别指标MPR的链接预测

多元网络通常是指节点之间存在多种维度链接关系的图结构.多元网络链接预测算法在构建相似度指标时,多数仅考虑单一维度网络的拓扑结构属性,未挖掘不同维度子网络之间存在的关联,影响链接预测的效果.针对该问题,提出一种基于多元全局节点影响力识别指标MPR的多元网络链接预测算法.通过定义一个多维度节点影响力排序指标MPR,度量多元网络空间中影响力较大的节点,并把影响力排名函数转化为潜在节点对之间的相似度得分,从而应用到多元网络链接预测场景中.在2个真实多元网络数据集上的实验结果表明,该算法的预测效果优于PR、EDC、ANC等对比算法,且具有较好的稳定性.     

一种融合节点属性信息的社会网络链接预测方法

随着大规模社会网络的发展,链接预测成为了一个重要的研究课题。研究了在社会网络中融合节点属性信息进行链接预测,在传统的社会-属性网络图模型的基础上,将节点属性的类别这一重要参量加入到网络构建中。基于此,提出了一系列为网络中不同类型的连边分配边权重的方法,最后通过随机游走的方法进行网络链接的预测。实验表明,所提链接预测方法相比同类方法有明显的效果提升。     

基于图卷积神经网络的完全图人脸聚类

人脸聚类是根据不同身份对人脸图像进行分组的方法,主要用于人脸标注和图像管理等领域.针对现有方法中存在大量冗余数据的问题,文中使用一种基于完全图约束和上下文关系进行链接预测的方法.该聚类算法基于图卷积神经网络进行链接预测,结合完全图约束筛选数据,同时在预测的过程中对链接关系进行不断的更新.实验结果显示,结合完全图约束的人脸聚类方法能够在减少冗余数据、加快运行速度的同时,提升聚类的准确率,从而提高聚类的整体效果.     

面向链接预测的知识图谱表示学习方法综述

作为人工智能的重要基石, 知识图谱能够从互联网海量数据中抽取并表达先验知识, 极大程度解决了智能系统认知决策可解释性差的瓶颈问题, 对智能系统的构建与应用起关键作用. 随着知识图谱技术应用的不断深化, 旨在解决图谱欠完整性问题的知识图谱补全工作迫在眉睫. 链接预测是针对知识图谱中缺失的实体与关系进行预测的任务, 是知识图谱构建与补全中不可或缺的一环. 要充分挖掘知识图谱中的隐藏关系, 利用海量的实体与关系进行计算, 就需要将符号化表示的信息转换为数值形式, 即进行知识图谱表示学习. 基于此, 面向链接预测的知识图谱表示学习成为知识图谱领域的研究热点. 从链接预测与表示学习的基本概念出发, 系统性地介绍面向链接预测的知识图谱表示学习方法最新研究进展. 具体从知识表示形式、算法建模方式两种维度对研究进展进行详细论述. 以知识表示形式的发展历程为线索, 分别介绍二元关系、多元关系和超关系知识表示形式下链接预测任务的数学建模. 基于表示学习建模方式, 将现有方法细化为4类模型: 平移距离模型、张量分解模型、传统神经网络模型和图神经网络模型, 并详细描述每类模型的实现方式与解决不同关系元数链接预测任务的代表模型. 在介绍链接预测的常用的数据集与评判标准基础上, 分别对比分析二元关系、多元关系和超关系3类知识表示形式下, 4类知识表示学习模型的链接预测效果, 并从模型优化、知识表示形式和问题作用域3个方面展望未来发展趋势.     

基于攻击模式的反向搜索攻击图生成算法

在使用攻击图方法分析网络中脆弱性之间关系时,网络规模一直是制约攻击图生成算法效率的根本因素.本文提出了一个基于攻击模式的高效攻击图反向生成算法.首先,对已有网络模型做出改进,提出了新型的基于网络中关键属性的模型,该模型使用子网掩码压缩网络连接关系,达到缩小网络规模的目的.其次,使用网络模型中的关键属性对脆弱性进行描述,...     

基于Skyline查询的社会网络链接预测

在社会媒体中,用户的状态信息实时地更新,用户之间的链接结构也不断改变,这给网络的链接预测提出了严峻的挑战。传统的链接预测方法针对某一特定情景,在非预定情景中效果往往表现不佳。针对单一网路连接预测算法的不足,提出一种基于Skyline查询的社会网络链接预测方法。该算法综合运用多种网络链接预测算法,将其预测值作为被预测链接的属性向量,并将Skyline点作为链接预测的结果返回给用户。实验表明,基于Skyline查询的链接预测方法其准确性明显高于相关链接预测研究的准确性,可应用于实际的社会媒体链接预测和推荐。     

基于属性关系图的同名实体区分算法

同名问题在大规模的数据库或者数字化图书馆中普遍存在,且困扰着许多研究课题。本文首先提出一种新的图结构——属性关系图(ARG)形象地刻画实体特征及实体间的联系,并给出一种基于属性关系图框架的同名区分算法ARG-Resolution,对共享同一名字的作者进行分析,根据他们之间的相似度将其聚类,最终得到对应真正实体的各个结果聚类。实验证明挖掘作者间的潜在连接进一步提高了同名区分的质量,成功解决了同名问题。     

基于随机游走的带有属性网络的链接预测

链接预测的问题是复杂网络分析中的一个重要研究领域,已经在社会学、生物信息学、信息科学以及计算机科学等领域得到了广泛的应用。提出了一个顶点具有属性的网络链接预测的随机游走算法。在此算法中,根据顶点和属性的链接相似度定义了每一条边上的传播概率。并将顶点的属性相似度作为顶点间的相似度的初值,然后根据传输概率在网络中以随机游走的方式进行传播和更新,最终得到顶点间的相似度作为链接预测的结果得分。实验结果显示,提出的算法在顶点带属性的网络中取得了比其他算法更精确的预测结果。     

基于标签相似度计算的学术圈构建方法

为面向学者的社交网络系统中的用户构建学术圈,对促进学者之间的交流具有重要的应用价值。根据学者之间的共同属性进行相似度计算,形成学术领域相似和研究课题相近的学术圈,能让学者们更加紧密和频繁地协同合作。提出了利用学者的学术信息提取代表个人特征的学术标签,并对不同类别标签的权重进行衡量,再通过相似度计算和聚类算法构建学术圈的方法。通过抓取学者社交网络平台SCHOLAT公开的学者信息进行实验,进而验证所提方法的可靠性和实用性。     

Learning to rank on graphs

Graph representations of data are increasingly common. Such representations arise in a variety of applications, including computational biology, social network analysis, web applications, and many others. There has been much work in recent years on developing learning algorithms for such graph data; in particular, graph learning algorithms have been developed for both classification and regression on graphs. Here we consider graph learning problems in which the goal is not to predict labels of objects in a graph, but rather to rank the objects relative to one another; for example, one may want to rank genes in a biological network by relevance to a disease, or customers in a social network by their likelihood of being interested in a certain product. We develop algorithms for such problems of learning to rank on graphs. Our algorithms build on the graph regularization ideas developed in the context of other graph learning problems, and learn a ranking function in a reproducing kernel Hilbert space (RKHS) derived from the graph. This allows us to show attractive stability and generalization properties. Experiments on several graph ranking tasks in computational biology and in cheminformatics demonstrate the benefits of our framework.     

Markov-Miml: A Markov chain-based multi-instance multi-label learning algorithm

The main aim of this paper is to propose an efficient and novel Markov chain-based multi-instance multi-label (Markov-Miml) learning algorithm to evaluate the importance of a set of labels associated with objects of multiple instances. The algorithm computes ranking of labels to indicate the importance of a set of labels to an object. Our approach is to exploit the relationships between instances and labels of objects. The rank of a class label to an object depends on (i) the affinity metric between the bag of instances of this object and the bag of instances of the other objects, and (ii) the rank of a class label of similar objects. An object, which contains a bag of instances that are highly similar to bags of instances of the other objects with a high rank of a particular class label, receives a high rank of this class label. Experimental results on benchmark data have shown that the proposed algorithm is computationally efficient and effective in label ranking for MIML data. In the comparison, we find that the classification performance of the Markov-Miml algorithm is competitive with those of the three popular MIML algorithms based on boosting, support vector machine, and regularization, but the computational time required by the proposed algorithm is less than those by the other three algorithms.     

Arnetminer: expertise oriented search using social networks

Expertise Oriented Search (EOS) aims at providing comprehensive expertise analysis on data from distributed sources. It is useful in many application domains, for example, finding experts on a given topic, detecting the confliction of interest between researchers, and assigning reviewers to proposals. In this paper, we present the design and implementation of our expertise oriented search system, Arnetminer (). Arnetminer has gathered and integrated information about a half-million computer science researchers from the Web, including their profiles and publications. Moreover, Arnetminer constructs a social network among these researchers through their co-authorship, and utilizes this network information as well as the individual profiles to facilitate expertise oriented search tasks. In particular, the co-authorship information is used both in ranking the expertise of individual researchers for a given topic and in searching for associations between researchers. We have conducted initial experiments on Arnetminer. Our results demonstrate that the proposed relevancy propagation expert finding method outperforms the method that only uses person local information, and the proposed two-stage association search on a large-scale social network is order of magnitude faster than the baseline method.     

Where is evolutionary computation going? A temporal analysis of the EC community

Studying an evolving complex system and drawing some conclusions from it is an integral part of nature-inspired computing; being a part of that complex system, some insight can also be gained from our knowledge of it. In this paper we study the evolution of the evolutionary computation co-authorship network using social network analysis tools, with the aim of extracting some conclusions on its mechanisms. In order to do this, we first examine the evolution of macroscopic properties of the EC co-authorship graph, and then we look at its community structure and its corresponding change along time. The EC network is shown to be in a strongly expansive phase, exhibiting distinctive growth patterns, both at the macroscopic and the mesoscopic level.

基于小样本集弱学习规则的KNN分类算法*

KNN及其改进算法使用类标号已知的数据集 对类标号未知的数据集 进行类别标识,如果 中的数据数量过少,将会影响最后的分类精度。基于小样本弱学习规则的KNN分类算法旨在提高基于小样本集的KNN算法的分类精度,它首先对 中的数据对象进行学习,从中选取一些数据,利用学到的标签知识对其进行类别标号,然后将其加入到 中,最后利用扩展后的 对 中的数据对象进行类别标识。通过使用标准数据集的测试发现该算法能够提高KNN的分类精度,取得了较满意的结果。     

基于压缩感知的社团结构深度学习方法

传统社团结构发现算法复杂度高,且只适合处理小规模低维度的社会网络数据,而无法处理大规模高维度实际网络数据。为此,提出一种基于压缩感知的社团结构深度学习方法。通过随机测量矩阵对社会网络数据进行特征降维,并使用深度信度网(DBN)对降维后的特征样本集进行无监督学习,利用带类标的小样本集进行有监督调优。仿真结果表明,随机测量方法对高维稀疏特征具有较好的降维效果,DBN对大规模数据集具有较好的处理性能,该方法适合对大规模高维度实际社会网络数据进行高效处理。     

Measuring similarity of individuals in description logics over the refinement space of conjunctive queries

Sensor networks, communication and financial networks, web and social networks are becoming increasingly important in our day-to-day life. They contain entities which may interact with one another. These interactions are often characterized by a form of autocorrelation, where the value of an attribute at a given entity depends on the values at the entities it is interacting with. In this situation, the collective inference paradigm offers a unique opportunity to improve the performance of predictive models on network data, as interacting instances are labeled simultaneously by dealing with autocorrelation. Several recent works have shown that collective inference is a powerful paradigm, but it is mainly developed with a fully-labeled training network. In contrast, while it may be cheap to acquire the network topology, it may be costly to acquire node labels for training. In this paper, we examine how to explicitly consider autocorrelation when performing regression inference within network data. In particular, we study the transduction of collective regression when a sparsely labeled network is a common situation. We present an algorithm, called CORENA (COllective REgression in Network dAta), to assign a numeric label to each instance in the network. In particular, we iteratively augment the representation of each instance with instances sharing correlated representations across the network. In this way, the proposed learning model is able to capture autocorrelations of labels over a group of related instances and feed-back the more reliable labels predicted by the transduction in the labeled network. Empirical studies demonstrate that the proposed approach can boost regression performances in several spatial and social tasks.