节点相似度标签传播在社会网络中的应用研究

近年来,社会网络簇结构挖掘取得了长足的进展,广泛应用在社会网、生物网和万维网等领域中。针对当前研究社会网络簇结构挖掘的热点问题,重点研究基于局部信息的聚类算法,并进行分析总结;对标签传播算法（LPA）进行深入研究与分析,针对该算法中由于随机策略而导致网络划分并非最优的缺陷,引入节点属性相似度的概念,提出LPA-SNA算法;采用美国大学足球赛程网络、科学家合著网络作为数据集,分别实现LPA算法与LPA-SNA算法,并对它们的性能进行比较。实验结果表明LPA-SNA较之原始的LPA算法,提高了网络聚类的质量,优化了聚类效果,同时降低了算法的时间开销,提高了算法聚类速度。     

Graph kernel based link prediction for signed social networks

By revealing potential relationships between users, link prediction has long been considered as a fundamental research issue in singed social networks. The key of link prediction is to measure the similarity between users. Existing works use connections between target users or their common neighbors to measure user similarity. Rich information available for link prediction is missing since use similarity is widely influenced by many users via social connections. We therefore propose a novel graph kernel based link prediction method, which predicts links by comparing user similarity via signed social network’s structural information: we first generate a set of subgraphs with different strength of social relations for each user, then calculate the graph kernel similarities between subgraphs, in which Bhattacharyya kernel is used to measure the similarity of the k-dimensional Gaussian distributions related to each k-order Krylov subspace generated for each subgraph, and finally train SVM classifier with user similarity information to predict links. Experiments held on real application datasets show that our proposed method has good link prediction performances on both positive and negative link prediction. Our method has significantly higher link prediction accuracy and F1-score than existing works.     

基于节点相似性度量的社团结构划分方法

针对复杂网络结构划分过程复杂、准确性差的问题,定义了节点全局和局部相似性衡量指标,并构建节点的相似性矩阵,提出一种基于节点相似性度量的社团结构划分算法.其基本思路是将节点(或社团)按相似性合并条件划分到同一个社团中,如果合并后的节点(或社团)仍然满足相似性合并条件,则继续合并,直到所有节点都得到准确的社团划分.实验结果表明,所提算法能成功正确地划分出真实网络中的社团结构, 性能比标签传播算法(LPA)、GN(Girvan-Newman)、CNM(Clauset-Newman-Moore)等算法优秀,能有效提高结果的准确性和鲁棒性.     

Detecting and predicting privacy violations in online social networks

Online social networks have become an essential part of social and work life. They enable users to share, discuss, and create content together with various others. Obviously, not all content is meant to be seen by all. It is extremely important to ensure that content is only shown to those that are approved by the content’s owner so that the owner’s privacy is preserved. Generally, online social networks are promising to preserve privacy through privacy agreements, but still everyday new privacy leakages are taking place. Ideally, online social networks should be able to manage and maintain their agreements through well-founded methods. However, the dynamic nature of the online social networks is making it difficult to keep private information contained. We have developed $\mathcal{PROTOSS}$ , a run time tool for detecting and predicting $\mathcal{PR}\mathrm{ivacy}\ \mathrm{vi}\mathcal{O}\mathrm{la}\mathcal{T}\mathrm{ions}\ \mathrm{in}\ \mathcal{O}\mathrm{nline}\ \mathcal{S}\mathrm{ocial}\ \mathrm{network}\mathcal{S}$ . $\mathcal{PROTOSS}$ captures relations among users, their privacy agreements with an online social network operator, as well as domain-based semantic information and rules. It uses model checking to detect if relations among the users will result in the violation of privacy agreements. It can further use the semantic information to infer possible violations that have not been specified by the user explicitly. In addition to detection, $\mathcal{PROTOSS}$ can predict possible future violations by feeding in a hypothetical future world state. Through a running example, we show that $\mathcal{PROTOSS}$ can detect and predict subtle leakages, similar to the ones reported in real life examples. We study the performance of our system on the scenario as well as on an existing Facebook dataset.     

社交网络中模块关系树的相似性算法的研究

提出一种基于模块关系树的分析方法,考虑每个实体与用户之间的兴趣、住址和共同好友等相关因素,制定不同的关系树,然后根据路径长度计算各因素的相关度值,最后综合每个实体模块,从而筛选出关系最密切的实体。实验结果证明,该算法能过滤掉大量无关信息,有效找出最相关的实体,提高了搜索结果的准确率。     

Microblogs recommendations based on implicit similarity in content social networks

With the development of online social networking applications, microblogs have become a necessary online communication network in daily life. Users are interested in obtaining personalized recommendations related to their tastes and needs. In some microblog systems, tags are not available, or the use of tags is rare. In addition, user-specified social relations are extremely rare. Hence, sparsity is a problem in microblog systems. To address this problem, we propose a new framework called Pblog to alleviate sparsity. Pblog identifies users’ interests via their microblogs and social relations and computes implicit similarity among users using a new algorithm. The experimental results indicated that the use of this algorithm can improve the results. In online social networks, such as Twitter, the number of microblogs in the system is high, and it is constantly increasing. Therefore, providing personalized recommendations to target users requires considerable time. To address this problem, the Pblog framework groups similar users using the analytic hierarchy process (AHP) method. Then, Pblog prunes microblogs of the target user group and recommends microblogs with higher ratings to the target user. In the experimental results section, the Pblog framework was compared with several other frameworks. All of these frameworks were run on two datasets: Twitter and Tumblr. Based on the results of these comparisons, the Pblog framework provides more appropriate recommendations to the target user than previous frameworks.

     

CSD: A multi-user similarity metric for community recommendation in online social networks

Communities are basic components in networks. As a promising social application, community recommendation selects a few items (e.g., movies and books) to recommend to a group of users. It usually achieves higher recommendation precision if the users share more interests; whereas, in plenty of communities (e.g., families, work groups), the users often share few. With billions of communities in online social networks, quickly selecting the communities where the members are similar in interests is a prerequisite for community recommendation. To this end, we propose an easy-to-compute metric, Community Similarity Degree (CSD), to estimate the degree of interest similarity among multiple users in a community. Based on 3460 emulated Facebook communities, we conduct extensive empirical studies to reveal the characteristics of CSD and validate the effectiveness of CSD. In particular, we demonstrate that selecting communities with larger CSD can achieve higher recommendation precision. In addition, we verify the computation efficiency of CSD: it costs less than 1 hour to calculate CSD for over 1 million of communities. Finally, we draw insights about feasible extensions to the definition of CSD, and point out the practical uses of CSD in a variety of applications other than community recommendation.     

基于节点相似性的容延/容断网络路由算法

针对容延/容断网络(DTN)网络的时延高、割裂频繁,以及节点缓存和能量受限等网络特性,为提高容延网络的传输率,同时降低网络开销和网络时延,提出了一种基于节点相似性的容延网络路由算法(RABNS)。该算法利用历史相遇信息预测节点未来相遇概率,并且把历史相遇的节点录入为集合,利用集合的交集运算来评估一对相遇节点的相似性,并以此为判定条件控制网络中的副本数量。在模拟器The ONE上采用RandomWaypoint运动模型进行仿真,其中RABNS在消息投递率方面优于PROPHET,网络负载约为PROPHET的50%,较大程度上提高了网络资源利用率;平均时延稍高于Epidemic但低于PROPHET,节点缓存空间大小对算法的平均跳数影响不大,且RABNS的平均跳数约为PROPHET的一半。仿真结果表明,RABNS能有效地限制消息洪泛,获取更高的消息投递率、更低的网络开销和数据时延,因此尤其适用于节点存储空间有限的DTN环境和具有群居特性的社交容延网络中。     

A promotive structural balance model based on reinforcement learning for signed social networks

Neural Computing and Applications - To solve the structural balance problem in signed social networks, a number of structural balance models have been developed. However, these models neglect the...     

A comparative analysis of evolutionary and memetic algorithms for community detection from signed social networks

To detect communities in signed networks consisting of both positive and negative links, two new evolutionary algorithms (EAs) and two new memetic algorithms (MAs) are proposed and compared. Furthermore, two measures, namely the improved modularity Q and the improved modularity density D-value, are used as the objective functions. The improved measures not only preserve all properties of the original ones, but also have the ability of dealing with negative links. Moreover, D-value can also control the partition to different resolutions. To fully investigate the performance of these four algorithms and the two objective functions, benchmark social networks and various large-scale randomly generated signed networks are used in the experiments. The experimental results not only show the capability and high efficiency of the four algorithms in successfully detecting communities from signed networks, but also indicate that the two MAs outperform the two EAs in terms of the solution quality and the computational cost. Moreover, by tuning the parameter in D-value, the four algorithms have the multi-resolution ability.     

可信链在Ad Hoc网络的传递

为了进一步提高Ad Hoc网络的安全性,提出一种利用可信平台模块传递信任链的方案。该方案以将信任关系从Ad Hoc网络节点扩展至Ad Hoc网络为设计目标,利用信任模型评估每个节点的信任度,在ARAN安全路由协议的基础上,结合信任度对ARAN安全路由协议进行了改进,选出一条可信度最高的路由,对可信链传递方案进行性能分析。     

社交网络中一种快速精确的节点影响力排序算法

在大规模在线社交网络中,通过对用户影响力进行排序找出其中最具影响力的节点（集合）是一个很重要的研究方向,对于有效控制信息扩散、舆情分析和控制、精准营销等均有重要的作用。已有的节点影响力排序算法或者需要网络的全局拓扑信息来计算单个节点影响力（如基于介数中心性的算法）而时间开销过大,不适用于大规模网络;或者基于传统的网页排序算法（如PageRank）而不能很好地处理社交网络中存在着大量“末梢”节点的问题以及不同用户之间的联系强度不同的问题。在传统的PageRank算法的基础上做出了两点改进。首先,通过在PageRank算法的权值回收步骤中考虑对不同的连接赋予不同的权值,有效避免了末梢节点带来的影响。其次,在PageRank算法的投票过程中考虑邻居个体的差异性,提出了一种基于半邻域信息的节点权值分配方法,有效提高了节点排序的准确度。在一个包含大约15 000个用户的样本网络中,我们所提出的改进算法能够找出前1 000个最有影响力的节点中的40%以上的节点,而传统的PageRank算法仅能找出其中11%的节点。同时,相比于基于介数中心性的算法,所提出的改进算法以小得多的时间开销达到了相近甚至更好的排序准确度。     

HSEM: highly scalable node embedding for link prediction in very large-scale social networks

World Wide Web - Very large-scale social networks are typically sparse and dynamic and often have millions of nodes and billions of links. Link prediction in very large-scale networks is a...     

Improving the readability of clustered social networks using node duplication

Exploring communities is an impor tant task in social network analysis. Such communities are currently identified using clustering methods to group actors. This approach often leads to actors belonging to one and only one cluster, whereas in real life a person can belong to several communities. As a solution we propose duplicating actors in social networks and discuss potential impact of such a move. Several visual duplication designs are discussed and a controlled experiment comparing network visualization with and without duplication is performed, using 6 tasks that are impor tant for graph readability and visual interpretation of social networks. We show that in our experiment, duplications significantly improve community-related tasks but sometimes interfere with other graph readability tasks. Finally, we propose a set of guidelines for deciding when to duplicate actors and choosing candidates for duplication, and alternative ways to render them in social network representations.     

基于节点动态属性相似性的社会网络社区推荐算法

社区推荐帮助用户寻找感兴趣的社群,是社会网络分析的重要内容。根据社会网络的动态变化特性,通过分析网络的动态演变过程、网络个体的行为特征及个体间联系的变化,研究动态社区及其个体的动态特性的形式化描述方法,提出了节点（个体）间的动态属性相似度计算方法和基于节点（个体）间的动态属性相似度计算的社区推荐算法,可以克服通过个体的直接联系进行社区推荐的局限性。实验结果表明,应用本算法进行社区推荐的准确率有较大提高,能有效应用于动态社会网络的社区推荐。     

Strategies for predicting local trust based on trust propagation in social networks

Trust plays a critical role in determining social interactions in both online and offline networks, and reduces information overload, uncertainties and risk from unreliable users. In a social network, even if two users are not directly connected, one user can still trust the other user if there exists at least one path between the two users through friendship networks. This is the result of trust propagation based on the transitivity property of trust, which is “A trusts B and B trusts C, so A will trust C”. It is important to provide a trust inference model to find reliable trust paths from a source user to an unknown target user, and to systematically combine multiple trust paths leading to a target user. We propose strategies for estimating level of trust based on Reinforcement Learning, which is particularly well suited to predict a long-term goal (i.e. indirect trust value on long-distance user) with short-term reward (i.e. direct trust value between directly connected users). In other words, we compare and evaluate how the length of available trust paths and aggregation methods affects prediction accuracy and then propose the best strategy to maximize the prediction accuracy.     

Recommending diverse friends in signed social networks based on adaptive soft consensus paradigm using variable length genetic algorithm

Despite the strategic role played by individuals, who act as intermediaries between distinct groups of people, the problem of recommending diverse friends in signed social networks (SSNs) still remains largely unexplored. Our model integrates homophily and diversity to develop an adaptive consensus based framework, which involves fuzzy group decision making analysis by leveraging on the signed social links and underlying users’ preferences, to offer lists of connections which are diverse as well as relevant. Our contributions are three-fold. First, we modeled the fuzzy binary adjacency relations between users, thereafter referred as decision makers (DMs), exploiting users’ preferences conferred on a set of items, and then higher order fuzzy m-ary adjacency relations are constructed to represent the grade of agreement between a set of m DMs. Further, in order to evaluate the relevance of each decision maker involved in the decision making process, we introduce a novel diversity measure based on the knowledge of socio-psychological theories and the information contained in social and interest links. Next, by employing variable-length genetic algorithm, an idea of adaptive consensus is explored to evolve groups of experts which are highly consensual as well as influential in the social network. Finally, on the basis of opinions gleaned from the members of these groups, sign of unknown links are predicted, thereby generating a top-N recommendations list of diverse friends. Extensive experimental study conducted on Epinions dataset illustrates that our proposed scheme outperforms the traditional graph-based methods.     

融合局部与全局紧密度的符号网络链接预测算法

鉴于大多数符号网络预测算法仅能对已有链接缺失的符号进行预测,无法实现未知的链接及其符号预测,提出一种融合局部与全局结构特征定义节点间相似性的符号网络链接预测算法.基于结构平衡理论,利用连接两节点的步长为2和3的路径信息分别定义局部和全局链接紧密度,有效融合两者得到两节点的总相似度,其绝对值度量了链接建立的可能性,其符号即为链接的符号预测结果.在多个经典的符号网络数据集上对算法的有效性和正确性进行了验证,并与符号网络中有代表性的预测算法进行了准确率以及推荐链接的对比分析.结果显示,所提算法在链接预测与符号预测两方面均达到了较好的预测性能.