The purpose of the click-through rate is to predict the probability that a user is most likely to click on a recommended item, garnering extensive attention in both academia and industry. In recent studies, it has been shown that high-quality user representation and feature interaction contribute significantly to improving accuracy in prediction tasks. However, the current methods still face two challenging problems. First, the behavior sequences contain complex interest features, and it is difficult to effectively capture the latent dominant interests. Besides, most models neglect the latent synergy between fine-grained features (i.e., they pay less attention to key feature interaction). To address these problems, in this paper, a target item-enhanced parallel fusion network (PFN) is proposed. First, the user’s historical interests are enhanced through a transformer. Then, the Pearson function is employed to gauge the strength of the relationship between the enhanced interest features and the target item, thus accentuating the user’s latent dominant interests. Third, feature interaction is learned via an equal interaction network, and then a soft-attention network is used to filter out unnecessary noise and retain fine-grained feature interaction to enhance the expressive ability of latent feature synergies. In addition, a multi-layer perceptron network is used to model the above features and learn the high-order representation of users’ more relevant interests. We have conducted extensive experiments on four public datasets and the PFN shows excellent performance.

While the Internet is open by design, it is still the case that users can be subject to censorship by governments or enterprises in accessing Web services and data. In this paper we propose SEnD, a fully-distributed censorship circumvention system built upon an overlay, where users have peer-to-peer virtual private IP tunnels to proxies within their social network. With SEnD, users in an uncensored area can act as proxy servers for their social friends in a censored area, allowing them to bypass the censorship. SEnD is able to outperform the current censorship techniques, such as IP address blocking and active probing attacks. We assessed the effectiveness of SEnD through extensive simulations based on a synthetic dataset, as well as experiments based on a prototype implementation. We built our synthetic dataset based on parameters obtained from questionnaires administered both inside and outside China (we consider China as a case study of censorship area). The results show that SEnD is feasible, efficient and scalable. For example, when the proportion of concurrent active users is less than 60, 99.9 percent of these users are able to find proxy servers.

Abstract In cognitive radio networks (CRNs), users can collaborate to improve the accuracy of spectrum sensing, but a large number of secondary users reporting their local sensing results may create significant overhead. In this paper, we propose a new pre‐sensing scheme, called preload cooperative sensing (PCS), which not only attains the given sensing accuracy for CRNs but also reduces the whole sensing timeT. In order to reduce the sensing overhead in CRNs, the proposed scheme adopts two key technologies: selective reporting technology and pre‐sensing sequential detection technology. Selective reporting technology implies that only those users, which detect the presence of primary users, need to report the results, while pre‐sensing sequential detection technology is an asynchronous parallel scheme, which sets a threshold to determine the presence of primary users. Considering the preload sensing slots, we derive a formula to express the overall miss detection probability, and at a given Quality of Service (QoS) value, the sensing overheads of PCS are analyzed over Rayleigh fading channel. Also, we consider the overhead minimization problems in PCS. Simulation results show the superiority and efficiency of the PCS scheme. Copyright © 2015 John Wiley & Sons, Ltd.

This paper is concerned with the problem of how to share distributed resources. Based on a distributed resource sharing application in schools, an HRRP(k) network is proposed and its properties studied. It is proven that the HRRP(k) network has better performance than a 2-D mesh in group communication. Then, to improve the quality of service (QoS) of the education resource sharing network, several key strategies are proposed, including the strategy for a node to join or leave the system, the strategy for searching for resources, and the strategy for setting up connections between nodes. To realize local and global resource retrieval, several algorithms based on the HRRP(k) network are proposed. Finally, the advantages of the HRRP(k) network and the effectiveness of proposed strategies are established by theoretical analysis and comparison. Based on these findings, a prototype of a resource sharing application is proposed, which shows the HRRP(k) network has a better performance than alternative network architectures.

An interconnection network, RP(k), and its properties are investigated. Two parameters, the closest group and the optimal partition of networks are proposed. It is shown that RP(k) network has high communication efficiency . It is also proven that RP(k) network is a Hamiltonian graph and the ring can be embedded into the RP(k) network with load, expansion, dilation and congestion all equal to 1 even though some faulty nodes exist in the RP(k) network. Embedding of Rings and 2-D meshes into the RP(k) networks are discussed. Two embedding methods are given with high embedding performance.