Search

Incentive mechanisms based on networks reciprocity encourage rational peers take an active part in social Peer-to-Peer systems. While users switch altruism partners promptly, the cooperative behavior among network groups prevails in such self-organizing systems. To further analyze the effect of partner switching rules on the evolution of cooperation, we construct a spatial Prisoner's Dilemma game model and study the coevolution of behavior strategies, social relationships of individuals and their dynamic attributes. The age of a peer, as an intrinsic property relevant to its lifetime, influences the social pattern in the realistic situation that users with the similar ages often interact actively and frequently. Accordingly we propose a new mode of partner selection based on the dynamic tag, such as the system age or strategy age. Moreover, the similarity of individual ages is introduced to the strength of relationship that determines the stability of edges in the weighted graph. Simulation results indicate that the coevolution makes an effective improvement in the survival of cooperation. The dynamic rules depress the selfish behavior in the adaptive networks more than the static rule. And the strategy aging law, in particular, has a positive influence on cooperation because it favors the forming of prosocial links and cooperative clusters.

Multi-view data are prevalent in both machine learning and artificial intelligence. A panoply of multi-view clustering algorithms have been proposed to deal with multiview data. However, most of them just blindly concatenate all the views in spite of characteristic of different views. Self-paced learning is a kind of learning scheme which comes from human learning. It progresses from easy example to complex example during learning process. In analogy with these intuitions, we can learn the easiness of multiple views. Therefore, in this paper, we first present a new Self-Paced Learning Regularizer which is a kind of mixture weighting scheme to allocate different weight to the different view by considering views’ complexity. To recap the effectiveness of our self-paced learning regularizer, we propose a novel self-paced learning based multi-view spectral clustering algorithm(SPLMVC), which can define complexity across views and then automatically assign weight to each view. Extensive experiments on real-world multi-view datasets reveal its strength by comparison with other state-of-art methods.

The success of P2P systems ultimately depends on whether rational users will contribute their services. In five rules that Nowak generalized supporting cooperation, reciprocity mechanisms are usually utilized in P2P networks. As a tradition incentive mechanism, reputation based on indirect reciprocity is frequently designed to punish free-riders. Recent studies present social relationship among peers can be used to enhance the performances of P2P applications. In this paper we construct a spatial PD game with three strategies to investigate the impact of spatial reciprocity on the evolution of cooperation in reputation systems. In the practice case where learning environments differ from interaction environments, the structures of interaction and learning neighborhood have been discussed separately on ER networks. Simulation results demonstrate that the indirect mechanism by image score favors the cooperative behaviors among the structured population. In Particular, interaction network dramatically affects the stationary fractions of defectors. And learning networks take weaker impact on the evolution of cooperation. Similar conclusions have been drawn extensive simulations on regular random networks with different neighborhood size N and on BA scale-free networks as well. The current results are helpful to deeply understand the emergence of cooperative behaviors in social P2P systems.

Social networks have become popular research area in recent years. Evolution of Cooperation on complex networks, which provides a theoretical analysing framework for the social cooperation issue, has also been studied deeply in recent works. In this paper, we investigate evolutionary prisoner's dilemma game when individuals hold mixed strategies instead of pure strategies on cooperative networks. Firstly, the effect of payoff matrix on the average rate of cooperation is studied and we found that the value of the upper threshold of payoff matrix' parameters for high level of cooperation. Secondly, the influence of the strategy-updating probability P is studied. We found it is not conducive to the emergence of cooperation if the value of P is too big or too small. Thirdly, the time step F per round is also studied and we found the system is not conducive to the survival of the co operator when F is too small. This work may reveal the evolution of cooperation when mixed strategies are adopted and be helpful for understanding cooperative behavior under the environment of complex strategies.

In peer-to-peer (P2P) network, incentive mechanism is crucial to encourage cooperation among peers. Hence, how to construct a framework to analyze and evaluate the effectiveness of incentive mechanism is a very significant problem. Considering the peers' interactions are influenced by the network structure in real network, we propose a novel framework based on spatial evolutionary game theory. Different from most of other researches based on classical and evolutionary game theory, square lattice network is adopted as the network structure in this paper, without the assumption that peers are well-mixed in P2P network. The square lattice network structure can be easily extended to other realistic complex networks, such as small-world network and scale-free network. The reciprocative incentive mechanism is analyzed and evaluated under the framework with different service benefit. Through the simulation, the range of the parameter Q (cost/benefit) that makes the incentive mechanism work effectively under the framework is got, and the reason is analyzed. In addition, the influences of zero-cost identity and strategy mutation of peers on the incentive mechanism are evaluated. The framework is general to analyze and evaluate the effectiveness of other incentive mechanisms.

Cooperation within selfish individuals can be promoted by natural selection only in the presence of an additional mechanism. In this paper, we focus on an indirect reciprocity mechanism in dynamical structured populations. In social networks rational individuals update their strategies and adjust their social relationships. We propose a three-strategy prisoner's dilemma game model to investigate the evolution of cooperation on dynamical networks. In the coevolution of state and structure process, reciprocators adapt their behaviors and switch their partners based on reputation. Simulation results show that the dynamics of strategies and links can promote cooperation provided the partners switch proceeds much faster than the strategy updating.

In this paper, a new Gabor-based Kernel Independent Component Analysis (GKICA) method for face recognition is presented. This method first derives a Gabor feature vector from a set of down-sampled Gabor wavelet representations of face images, then reduces the dimensionality of the vector by means of kernel principal component analysis, and finally defines the independent Gabor kernel features based on the Independent Component Analysis (ICA). Experiments are performed to test the proposed algorithm on ORL dataset and Yale dataset. Results show that our new algorithm achieves higher recognition rates than ICA and Kernel Independent Component Analysis (KICA), and costs less time than Gable-based ICA (GICA).