求解互补问题的极大熵社会认知算法

针对传统算法无法获得互补问题的多个最优解的困难,提出了求解互补问题的社会认知优化算法.通过利用NCP函数,将互补问题的求解转化为一个非光滑方程组问题,然后用凝聚函数对其进行光滑化,进而把互补问题的求解转化为无约束优化问题,利用社会认知算法对其进行求解.该算法是基于社会认知理论,通过一系列的学习代理来模拟人类的社会性以及智能性从而完成对目标的优化.该算法对目标函数的解析性质没有要求且容易实现,数值实验结果表明了该方法是有效的.     

A game-theoretic framework to identify overlapping communities in social networks

In this paper, we introduce a game-theoretic framework to address the community detection problem based on the structures of social networks. We formulate the dynamics of community formation as a strategic game called community formation game: Given an underlying social graph, we assume that each node is a selfish agent who selects communities to join or leave based on her own utility measurement. A community structure can be interpreted as an equilibrium of this game. We formulate the agents’ utility by the combination of a gain function and a loss function. We allow each agent to select multiple communities, which naturally captures the concept of “overlapping communities”. We propose a gain function based on the modularity concept introduced by Newman (Proc Natl Acad Sci 103(23):8577–8582, 2006), and a simple loss function that reflects the intrinsic costs incurred when people join the communities. We conduct extensive experiments under this framework, and our results show that our algorithm is effective in identifying overlapping communities, and are often better then other algorithms we evaluated especially when many people belong to multiple communities. To the best of our knowledge, this is the first time the community detection problem is addressed by a game-theoretic framework that considers community formation as the result of individual agents’ rational behaviors.     

Minimum positive influence dominating set and its application in influence maximization: a learning automata approach

In recent years, with the rapid development of online social networks, an enormous amount of information has been generated and diffused by human interactions through online social networks. The availability of information diffused by users of online social networks has facilitated the investigation of information diffusion and influence maximization. In this paper, we focus on the influence maximization problem in social networks, which refers to the identification of a small subset of target nodes for maximizing the spread of influence under a given diffusion model. We first propose a learning automaton-based algorithm for solving the minimum positive influence dominating set (MPIDS) problem, and then use the MPIDS for influence maximization in online social networks. We also prove that by proper choice of the parameters of the algorithm, the probability of finding the MPIDS can be made as close to unity as possible. Experimental simulations on real and synthetic networks confirm the superiority of the algorithm for finding the MPIDS Experimental results also show that finding initial target seeds for influence maximization using the MPIDS outperforms well-known existing algorithms.     

Minimizing the expected complete influence time of a social network

Complete influence time specifies how long it takes to influence all individuals in a social network, which plays an important role in many real-life applications. In this paper, we study the problem of minimizing the expected complete influence time of social networks. We propose the incremental chance model to characterize the diffusion of influence, which is progressive and able to achieve complete influence. Theoretical properties of the expected complete influence time under the incremental chance model are presented. In order to trade off between optimality and complexity, we design a framework of greedy algorithms. Finally, we carry out experiments to show the effectiveness of the proposed algorithms.     

Cooperative Understanding of Utterances and Gestures in a Dialogue-Based Problem Solving System

A dialogue plays an important role in learning how to solve a problem and form a concept. We are developing a problem solving and knowledge acquisition system based on co-reference between drill texts and dialogue with a teacher, focusing on first-grade mathematics. This paper presents a method of cooperative understanding of utterances and gestures within dialogue. We first describe our system design principles, which provide the basis for the integration of multimodal information during a dialogue. We define a principle of complementarity, explain its implementation, and describe the architecture of the problem solving system. We then show how to integrate our algorithms for utterance and gesture analysis within that software architecture. A feature-based approach is used for gesture recognition, derived from a sequence of images arising during the cooperative analysis of utterances. We conclude with an evaluation of the system against the design principles.     

社会网络中的影响力最大化问题

影响力最大化问题要求在网络中选取若干节点,使得以它们为初始节点进行信息传播时,在网络中产生的影响能够达到最大。影响力最大化问题是近十年来社会网络中的研究热点之一,其研究不仅具有理论意义,并且还具有应用前景。介绍了影响力最大化问题产生的背景,分析了问题的研究现状、研究用的几种主要传播模型以及解决问题的几种主要算法。最后,讨论了该研究面临的一些问题,对未来可能发展的研究方向进行了展望。     

Retrieving the maximal time-bounded positive influence set from social networks

The appearance of social networks provides great opportunities for people to communicate, share and disseminate information. Meanwhile, it is quite challenge for utilizing a social networks efficiently in order to increase the commercial profit or alleviate social problems. One feasible solution is to select a subset of individuals that can positively influence the maximum other ones in the given social network, and some algorithms have been proposed to solve the optimal individual subset selection problem. However, most of the existing works ignored the constraint on time. They assume that the time is either infinite or only suitable to solve the snapshot selection problems. Obviously, both of them are impractical in the real system. Due to such reason, we study the problem of selecting the optimal individual subset to diffuse the positive influence when time is bounded. We proved that such a problem is NP-hard, and a heuristic algorithm based on greedy strategy is proposed. The experimental results on both simulation and real-world social networks based on the trace data in Shanghai show that our proposed algorithm outperforms the existing algorithms significantly, especially when the network structure is sparse.     

Maximizing influence under influence loss constraint in social networks

Influence maximization is a fundamental research problem in social networks. Viral marketing, one of its applications, aims to select a small set of users to adopt a product, so that the word-of-mouth effect can subsequently trigger a large cascade of further adoption in social networks. The problem of influence maximization is to select a set of K nodes from a social network so that the spread of influence is maximized over the network. Previous research on mining top-K influential nodes assumes that all of the selected K nodes can propagate the influence as expected. However, some of the selected nodes may not function well in practice, which leads to influence loss of top-K nodes. In this paper, we study an alternative influence maximization problem which is naturally motivated by the reliability constraint of nodes in social networks. We aim to find top-K influential nodes given a threshold of influence loss due to the failure of a subset of R(<K) nodes. To solve the new type of influence maximization problem, we propose an approach based on constrained simulated annealing and further improve its performance through efficiently estimating the influence loss. We provide experimental results over multiple real-world social networks in support. This research will further support practical applications of social networks in various domains particularly where reliability would be a main concern in a system deployment.     

Algorithms for nonnegative independent component analysis

We consider the task of solving the independent component analysis (ICA) problem x=As given observations x, with a constraint of nonnegativity of the source random vector s. We refer to this as nonnegative independent component analysis and we consider methods for solving this task. For independent sources with nonzero probability density function (pdf) p(s) down to s=0 it is sufficient to find the orthonormal rotation y=Wz of prewhitened sources z=Vx, which minimizes the mean squared error of the reconstruction of z from the rectified version y/sup +/ of y. We suggest some algorithms which perform this, both based on a nonlinear principal component analysis (PCA) approach and on a geodesic search method driven by differential geometry considerations. We demonstrate the operation of these algorithms on an image separation problem, which shows in particular the fast convergence of the rotation and geodesic methods and apply the approach to a musical audio analysis task.     

A self-adapted method for the categorization of social resources

Social tagging systems have become a popular system to organize information in many web 2.0 sites. They are also being rapidly adopted in enterprises to enhance information sharing, knowledge sharing and emerged as a novel categorization scheme based on the collective knowledge of people.Scalability is an issue of the categorization of the resources of social tagging systems. Scalability has highlighted a critical trade-off between accuracy and complexity. As social tagging systems evolve over time, resource categories can appear or disappear either by grouping new resources or disaggregating existing ones, and this implies the re-assignation of the resources involved to others categories. This makes the methods and/or algorithms that categorize resources of social tagging systems to be non-scalable, and then not efficiently implementable on real social tagging systems. This paper presents a simple method for categorizing resources on social tagging systems which is self-adaptive, scalable and implementable in any real social tagging system.     

Finding overlapping communities in a complex network of social linkages and Internet of things

Online social networks play an important role in today’s Internet. These social networks contain huge amounts of data and the integrated framework of SN with Internet of things (IoT) presents a challenging problem. IoT is the ubiquitous interconnection of everyday items of interest (things), providing connectivity anytime, anywhere, and with anything. Like biological, co-authorship, and virus-spread networks, IoT and Social Network (SN) can be characterized to be complex networks containing substantial useful information. In the past few years, community detection in graphs has been an active area of research (Lee and Won in Proceedings of IEEE SoutheastCon, pp. 1–5, 2012). Many graph mining algorithms have been proposed, but none of them can help in capturing an important dimension of SNs, which is friendship. A friend circle expands with the help of mutual friends, and, thus, mutual friends play an important role in social networks’ growth. We propose two graph clustering algorithms: one for undirected graphs such as Facebook and Google+, and the other for directed graphs such as Twitter. The algorithms extract communities, and based on the access control policy nodes share resources (things). In the proposed Community Detection in Integrated IoT and SN (CDIISN) algorithm, we divide the nodes/actors of complex networks into basic, and IoT nodes. We, then, execute the community detection algorithm on them. We take nodes of a graph as members of a SN, and edges depicting the relations between the nodes. The CDIISN algorithm is purely deterministic, and no fuzzy communities are formed. It is known that one community detection algorithm is not suitable for all types of networks. For different network structures, different algorithms exhibit different results, and methods of execution. However, in our proposed method, the community detection algorithm can be modified as desired by a user based on the network connections. The proposed community detection approach is unique in the sense that a user can define his community detection criteria based on the kind of network.     

Knowledge-based function optimization using fuzzy culturalalgorithms with evolutionary programming

In this paper, the advantages of a fuzzy representation in problem solving and search is investigated using the framework of Cultural algorithms (CAs). Since all natural languages contain a fuzzy component, the natural question is "Does this fuzzy representation facilitate the problem-solving process, within these systems". In order to investigate this question we use the CA framework of Reynolds (1996), CAs are a computational model of cultural evolution derived from and used to express basic anthropological models of culture and its development. A mathematical model of a full fuzzy CA is developed there. In it, the problem solving knowledge is represented using a fuzzy framework. Several theoretical results concerning its properties are presented. The model is then applied to the solution of a set of 12 difficult, benchmark problems in nonlinear real-valued function optimization. The performance of the full fuzzy model is compared with 8 other fuzzy and crisp architectures. The results suggest that a fuzzy approach can produce a statistically significant improvement in search efficiency over nonfuzzy versions for the entire set of functions, the then investigate the class of performance functions for which the full fuzzy system exhibits the greatest improvements over nonfuzzy systems. In general, these are functions which require some preliminary investigation in order to embark on an effective search.     

Efficient algorithms for influence maximization in social networks

In recent years, due to the surge in popularity of social-networking web sites, considerable interest has arisen regarding influence maximization in social networks. Given a social network structure, the problem of influence maximization is to determine a minimum set of nodes that could maximize the spread of influences. With a large-scale social network, the efficiency and practicability of such algorithms are critical. Although many recent studies have focused on the problem of influence maximization, these works in general are time-consuming when a social network is large-scale. In this paper, we propose two novel algorithms, CDH-Kcut and Community and Degree Heuristic on Kcut/SHRINK, to solve the influence maximization problem based on a realistic model. The algorithms utilize the community structure, which significantly decreases the number of candidates of influential nodes, to avoid information overlap. The experimental results on both synthetic and real datasets indicate that our algorithms not only significantly outperform the state-of-the-art algorithms in efficiency but also possess graceful scalability.     

一种用于进化算法历史计算数据的高效利用方法

进化算法由于其强大的系统建模能力和空间搜索能力已被广泛应用于许多实际问题的求解中。然而,在算法进化的过程中存在个体适应值重复计算的问题,尤其在解决实际工程中的复杂问题时,适应值的计算会消耗大量时间。为此,利用哈希表的高速存取能力,将哈希表用于存取适应值的历史计算数据,从而避免优化过程中适应值的重复计算,并且对优化结果没有任何影响。仿真实验结果验证了此方法的有效性。     

The role of social sentiment in stock markets: a view from joint effects of multiple information sources

Social sentiment reflects grassroots views regarding stock trends and has played a leading role in stock movements. Previous studies have relied predominantly on statistical models, regression models or vector-based predictive models to analyze the influence of social sentiment without considering other information sources or their intrinsic interactions. However, stock movements are in essence driven by various types of highly interrelated information sources including firm characteristics, social sentiment, and professional opinions. This paper describes the degree to which the problem arises in understanding the role of social sentiment in financial markets and proposes a novel intelligent stock analysis system to solve it. It first captures social sentiment and professional opinions from textual information in social media and financial news, respectively, and then represents the whole market information space consisting of these two information sources along with firm characteristics via tensors. Finally, a tensor-based learning algorithm is utilized to capture the interactions of these information sources on stock movements. Experiments performed on an entire year of data of China Securities Index (CSI 100) stocks demonstrate the effectiveness of the proposed intelligent system to study the role of social sentiment from the perspective of joint effects of multiple information sources compared with traditional vector-based systems.     

一种新的社会化相似度计算方法

基于社交网络的推荐算法引入社交网络信息到协同过滤算法中来, 使得用户朋友的偏好能够影响用户本身的偏好 。这些算法需要用到用户之间的相似度信息。目前有两个流行的基于共同评分项目集的相似度计算函数（VSS、PCC）。在很多情况下, 由于用户间没有共同评分项目集, 故无法计算他们之间的相似度。为了解决这个问题, 提出了一种基于矩阵分解的新的社会化相似度计算方法。在真实的包含社交网络的数据集上进行实验验证, 该方法的性能优于几个经典的基于社交网络的协同过滤算法, 而且能够解决新用户的冷启动问题。     

Parallel quantum-inspired evolutionary algorithms for community detection in social networks

The world around us may be viewed as a network of entities interconnected via their social, economic, and political interactions. These entities and their interactions form a social network. A social network is often modeled as a graph whose nodes represent entities, and edges represent interactions between these entities. These networks are characterized by the collective latent behavior that does not follow trivially from the behaviors of the individual entities in the network. One such behavior is the existence of hierarchy in the network structure, the sub-networks being popularly known as communities. Discovery of the community structure in a social network is a key problem in social network analysis as it refines our understanding of the social fabric. Not surprisingly, the problem of detecting communities in social networks has received substantial attention from the researchers.In this paper, we propose parallel implementations of recently proposed community detection algorithms that employ variants of the well-known quantum-inspired evolutionary algorithm (QIEA). Like any other evolutionary algorithm, a quantum-inspired evolutionary algorithm is also characterized by the representation of the individual, the evaluation function, and the population dynamics. However, individual bits called qubits, are in a superposition of states. As chromosomes evolve individually, the quantum-inspired evolutionary algorithms (QIEAs) are intrinsically suitable for parallelization.In recent years, programmable graphics processing units — GPUs, have evolved into massively parallel environments with tremendous computational power. NVIDIA® compute unified device architecture (CUDA®) technology, one of the leading general-purpose parallel computing architectures with hundreds of cores, can concurrently run thousands of computing threads. The paper proposes novel parallel implementations of quantum-inspired evolutionary algorithms in the field of community detection on CUDA-enabled GPUs.The proposed implementations employ a single-population fine-grained approach that is suited for massively parallel computations. In the proposed approach, each element of a chromosome is assigned to a separate thread. It is observed that the proposed algorithms perform significantly better than the benchmark algorithms. Further, the proposed parallel implementations achieve significant speedup over the serial versions. Due to the highly parallel nature of the proposed algorithms, an increase in the number of multiprocessors and GPU devices may lead to a further speedup.     

Maintaining Retrieval Knowledge in a Case-Based Reasoning System

The knowledge stored in a case base is central to the problem solving of a case-based reasoning (CBR) system. Therefore, case-base maintenance is a key component of maintaining a CBR system. However, other knowledge sources, such as indexing and similarity knowledge for improved case retrieval, also play an important role in CBR problem solving. For many CBR applications, the refinement of this retrieval knowledge is a necessary component of CBR maintenance. This article focuses on optimization of the parameters and feature selections/weights for the indexing and nearest-neighbor algorithms used by CBR retrieval. Optimization is applied after case-base maintenance and refines the CBR retrieval to reflect changes that have occurred to cases in the case base. The optimization process is generic and automatic, using knowledge contained in the cases. In this article we demonstrate its effectiveness on a real tablet formulation application in two maintenance scenarios. One scenario, a growing case base, is provided by two snapshots of a formulation database. A change in the company's formulation policy results in a second, more fundamental requirement for CBR maintenance. We show that after case-base maintenance, the CBR system did indeed benefit from also refining the retrieval knowledge. We believe that existing CBR shells would benefit from including an option to automatically optimize the retrieval process.     

基于位置信息的移动SNS数据动态划分复制算法

现有社交网络数据划分算法大多关注于好友关系和交互关系,忽略了位置信息,造成基于位置查询的响应时间较长。针对该问题,设计了一种移动社交网络双层社交图模型,该模型考虑了移动社交网络中用户交互行为的位置依赖性特点;并在此基础上提出了一种基于位置信息的移动社交网络数据动态划分复制算法MSDPR,该算法采用改进的K-Means算法对位置信息进行聚类,再根据聚类结果对数据进行划分,并利用社交关系进行数据的复制。实验结果表明:MSDPR算法在移动社交网络环境下能够有效地提高本地访问率,降低访问延迟,并且在动态加入数据时具有较好的适应性。