融合信任关系和用户项目二部图的推荐算法

传统冷启动和数据稀疏性问题是推荐系统面临的两大难题。现有的大多数基于矩阵分解的推荐方法将用户孤立对待,忽略了用户之间的信任关系,从而导致推荐性能低效。提出一种融合信任关系和用户项目二部结构的矩阵分解推荐方法。该方法在对评分矩阵进行分解的基础上,加入用户信任关系和用户项目二部图结构信息,采用梯度下降算法训练模型参数。Epinions数据集上的对比实验表明,该方法有效提高了推荐系统的准确性和可靠性,尤其在冷启动和稀疏数据情况下,其推荐精度明显优于传统的推荐方法。     

Collaborative filtering and deep learning based recommendation system for cold start items

Recommender system is a specific type of intelligent systems, which exploits historical user ratings on items and/or auxiliary information to make recommendations on items to the users. It plays a critical role in a wide range of online shopping, e-commercial services and social networking applications. Collaborative filtering (CF) is the most popular approaches used for recommender systems, but it suffers from complete cold start (CCS) problem where no rating record are available and incomplete cold start (ICS) problem where only a small number of rating records are available for some new items or users in the system. In this paper, we propose two recommendation models to solve the CCS and ICS problems for new items, which are based on a framework of tightly coupled CF approach and deep learning neural network. A specific deep neural network SADE is used to extract the content features of the items. The state of the art CF model, timeSVD++, which models and utilizes temporal dynamics of user preferences and item features, is modified to take the content features into prediction of ratings for cold start items. Extensive experiments on a large Netflix rating dataset of movies are performed, which show that our proposed recommendation models largely outperform the baseline models for rating prediction of cold start items. The two proposed recommendation models are also evaluated and compared on ICS items, and a flexible scheme of model retraining and switching is proposed to deal with the transition of items from cold start to non-cold start status. The experiment results on Netflix movie recommendation show the tight coupling of CF approach and deep learning neural network is feasible and very effective for cold start item recommendation. The design is general and can be applied to many other recommender systems for online shopping and social networking applications. The solution of cold start item problem can largely improve user experience and trust of recommender systems, and effectively promote cold start items.     

集成社会化标签和用户背景信息的协同过滤推荐方法

针对传统的协同推荐算法存在数据稀疏和推荐精度低的问题,提出了一种集成社会化标签和用户背景信息的协同过滤(CF)推荐方法。首先,分别计算基于社会化标签和用户背景信息的用户间的相似度;然后,基于用户评分计算用户间的相似度;最后,集成上述3种相似性度量产生用户间综合相似度,并对目标用户进行项目推荐。实验结果表明,与传统的协同过滤推荐算法相比,所提方法在正常数据集和冷启动数据集下的平均绝对误差(MAE)平均降低了16%和22.6%。该方法不仅能有效地提高推荐算法的精度,而且能较好地解决数据稀疏和冷启动的问题。     

融合信任关系和有用性评价的矩阵分解推荐方法

冷启动和数据稀疏性问题是推荐系统面临的两大难题。现有的大多数基于矩阵分解的推荐方法将用户孤立对待,忽略了用户之间的信任关系,导致推荐性能较低。提出一种融合信任关系和有用性评价的矩阵分解推荐方法。该方法在对评分矩阵进行概率分解的基础上,加入有用性评价和用户信任关系,采用交替最小二乘法训练模型参数。Epinions和Ciao数据集上的对比实验表明,所提方法有效提高了推荐系统的准确性和可靠性,尤其存在冷启动用户时,该方法的推荐精度明显优于传统的推荐方法。     

基于用户信任和兴趣的概率矩阵分解推荐方法

传统协同过滤推荐算法存在数据稀疏性、冷启动、新用户等问题.随着社交网络和电子商务的迅猛发展,利用用户间的信任关系和用户兴趣提供个性化推荐成为研究的热点.本文提出一种结合用户信任和兴趣的概率矩阵分解（STUIPMF）推荐方法.该方法首先从用户评分角度挖掘用户间的隐性信任关系和潜在兴趣标签,然后利用概率矩阵分解模型对用户评分信息、用户信任关系、用户兴趣标签信息进行矩阵分解,进一步挖掘用户潜在特征,缓解数据稀疏性.在Epinions数据集上进行实验验证,结果表明,该方法能够在一定程度上提高推荐精度,缓解冷启动和新用户问题,同时具有较好的可扩展性.     

Bayesian dual neural networks for recommendation

Most traditional collaborative filtering (CF) methods only use the user-item rating matrix to make recommendations, which usually suffer from cold-start and sparsity problems. To address these problems, on the one hand, some CF methods are proposed to incorporate auxiliary information such as user/item profiles; on the other hand, deep neural networks, which have powerful ability in learning effective representations, have achieved great success in recommender systems. However, these neural network based recommendation methods rarely consider the uncertainty of weights in the network and only obtain point estimates of the weights. Therefore, they maybe lack of calibrated probabilistic predictions and make overly confident decisions. To this end, we propose a new Bayesian dual neural network framework, named BDNet, to incorporate auxiliary information for recommendation. Specifically, we design two neural networks, one is to learn a common low dimensional space for users and items from the rating matrix, and another one is to project the attributes of users and items into another shared latent space. After that, the outputs of these two neural networks are combined to produce the final prediction. Furthermore, we introduce the uncertainty to all weights which are represented by probability distributions in our neural networks to make calibrated probabilistic predictions. Extensive experiments on real-world data sets are conducted to demonstrate the superiority of our model over various kinds of competitors.     

融合一致性社交关系的协同相似嵌入推荐模型

为了解决推荐系统中新用户评级预测冷启动和数据稀疏等问题,提出了一种融合一致性社交关系的协同相似嵌入推荐模型(collaborative similarity embedding recommendation model incorporating consistent social relationships, CSECSR)。首先,模型通过预热层对图形嵌入进行等权重传播和聚合;其次,采样具有一致性的社交关系邻居,并利用关系注意力机制对这些关系进行聚合;最后,利用用户和项目最终嵌入值的内积进行评分预测,设计具有自适应裕度的BPR损失和相似性损失的损失函数对模型进行优化。在Ciao、Epinions和FilmTrust数据集上与其他代表性的推荐模型进行了对比,实验结果表明所提推荐模型预测误差明显优于其他模型,证明了所提推荐模型的有效性。     

基于序贯三支神经网络的个性化推荐

虽然协同过滤可以实现用户的个性化推荐,但是大多数协同过滤及其改进模型未考虑用户和项目等特征,因而不能发掘样本间的非线性关系.与协同过滤相比,深度学习能挖掘丰富的用户兴趣模式,但网络拓扑结构是基于二支决策的方式,忽略了推荐样本的难易程度.为了增强模型的非线性表达,同时区分推荐样本的难易,受序贯三支决策的启发,提出序贯三支决策神经网络个性化推荐模型(personalized recommendation model based on sequential three-way decision with single feedforward neural network, STWD-SFNN-PR).首先,为了将高维稀疏特征向量映射为低维稠密的特征向量, STWD-SFNN-PR采用嵌入进行特征处理.其次,在增量式的网络结构中学习推荐样本,使用Adam优化网络参数,并返回难以推荐的样本.再次,利用序贯三支决策增加延迟决策的策略,并在不同的粒度层采用序贯的阈值,从而动态地实现难以推荐样本的划分.最后,为了验证模型的可行性和有效性,选择多种电影推荐数据集进行研究,并选择经典的神经网络推荐、经典的...     

Social network-based service recommendation with trust enhancement

Given the increasing applications of service computing and cloud computing, a large number of Web services are deployed on the Internet, triggering the research of Web service recommendation. Despite of service QoS, the use of user feedback is becoming the current trend in service recommendation. Likewise in traditional recommender systems, sparsity, cold-start and trustworthiness are major issues challenging service recommendation in adopting similarity-based approaches. Meanwhile, with the prevalence of social networks, nowadays people become active in interacting with various computers and users, resulting in a huge volume of data available, such as service information, user-service ratings, interaction logs, and user relationships. Therefore, how to incorporate the trust relationship in social networks with user feedback for service recommendation motivates this work. In this paper, we propose a social network-based service recommendation method with trust enhancement known as RelevantTrustWalker. First, a matrix factorization method is utilized to assess the degree of trust between users in social network. Next, an extended random walk algorithm is proposed to obtain recommendation results. To evaluate the accuracy of the algorithm, experiments on a real-world dataset are conducted and experimental results indicate that the quality of the recommendation and the speed of the method are improved compared with existing algorithms.     

Deep learning techniques for recommender systems based on collaborative filtering

In the Big Data Era, recommender systems perform a fundamental role in data management and information filtering. In this context, Collaborative Filtering (CF) persists as one of the most prominent strategies to effectively deal with large datasets and is capable of offering users interesting content in a recommendation fashion. Nevertheless, it is well-known CF recommenders suffer from data sparsity, mainly in cold-start scenarios, substantially reducing the quality of recommendations. In the vast literature about the aforementioned topic, there are numerous solutions, in which the state-of-the-art contributions are, in some sense, conditioned or associated with traditional CF methods such as Matrix Factorization (MF), that is, they rely on linear optimization procedures to model users and items into low-dimensional embeddings. To overcome the aforementioned challenges, there has been an increasing number of studies exploring deep learning techniques in the CF context for latent factor modelling. In this research, authors conduct a systematic review focusing on state-of-the-art literature on deep learning techniques applied in collaborative filtering recommendation, and also featuring primary studies related to mitigating the cold start problem. Additionally, authors considered the diverse non-linear modelling strategies to deal with rating data and side information, the combination of deep learning techniques with traditional CF-based linear methods, and an overview of the most used public datasets and evaluation metrics concerning CF scenarios.     

基于注意力机制的规范化矩阵分解推荐算法

近年来,矩阵分解(MF)技术因其有效性和简便性在推荐系统中得到广泛应用.但是,数据稀疏和冷启动问题导致MF学习到的用户特征向量不能准确地代表用户的偏好以及反映用户间的相似关系,影响了模型的性能.为了解决该问题,规范化矩阵分解(RMF)技术引起了研究者的关注.挖掘用户间可靠的相似关系,是RMF需要解决的问题.此外,MF将目标用户特征向量和目标项目特征向量的内积作为目标用户对目标项目的评分,这种简单的线性关系忽略了用户对项目各个属性特征不同的关注度.如何分析用户对项目属性特征的关注度,获取用户更准确的偏好,仍然是一个挑战.针对上述问题,提出了基于注意力机制的规范化矩阵分解模型(ARMF).具体地,为了获取用户间可靠的相似关系解决数据稀疏和冷启动问题,该模型同时依据用户信任网络和评分记录构建用户-项目异构网络,并基于该异构网络挖掘用户间的相似关系;为了进一步提升模型性能,通过在MF中引入注意力机制,分析用户对项目各个属性特征不同的关注度来获取用户更准确的偏好.最后,在两个真实数据集上对比ARMF与现有工作,实验结果证明,ARMF有更好的准确性和健壮性.     

Internet服务管理技术综述

1 服务与服务的分类经常提到服务这个概念,那么到底什么是服务呢?文[1]对服务进行了定义:服务就是服务提供方向一个或多个所服务的用户提供的一组实际能力。为研究之便,我们将服务分成两类:一类是传输服务,另一类是应用服务。这两种服务并不完全独立,它们是相互依存的,其中传输服务是应用服务的基础与保证,而应用服务是对传输服务的一种增值与体现。应用     

Modeling online service discontinuation with nonparametric agents

The internet and world wide web are an increasingly important resource, both as a market and as an information source, to both individual users and business entities. An estimated 120 million active web users exist in the United States alone. Access to these electronic marketplaces and information sources is accomplished through either a direct internet connection or through a service provider. Internet service providers (ISPs) enable internet and web access for most of these users either via dial-up modems (62.2 percent), or DSL connections (17 percent). Customers of ISPs frequently switch or discontinue service. The model selection perspective is used to extend previous work in this area through the development of a multi-agent system with neural network wrappers. The nonparametric (neural network) agents identify over 92 percent of those users that either stop or change service, which is a 15 percent increase over previous models.     

幂律特性在新浪微博个性化推荐中的应用研究

在社交网络数据中,幂率分布是数据的基本规律,幂率分布的长尾部分数据有明显的稀疏性,长尾推荐一直是推荐系统的挑战,而冷启动、数据稀疏和覆盖率这些问题也是推荐系统的重要研究内容。通过分析数据幂律分布的特性,在研究社交网络个性化推荐方法的基础上,结合社交网络用户行为数据反映出来的幂律分布特性,通过极大似然估计数据幂律分布的标度值。结合幂率特性改进了相似度计算方法,提出了一种基于幂率特性的混合推荐方法 PowerLawCF。最后,使用新浪微博的用户签到数据进行对比分析,PowerLawCF算法的推荐效果有显著提升,提高了长尾推荐的效果,对推荐系统的数据稀疏性和冷启动问题解决效果较好,说明基于幂律分布特征的推荐方法在推荐系统中的应用有积极的效果。     

神经网络水印技术研究进展

随着深度神经网络的推广应用,训练后的神经网络模型已经成为一种重要的资产并为用户提供服务.服务商在提供服务的同时,也更多地关注其模型的版权保护,神经网络水印技术应运而生.首先,分析水印及其基本需求,并对神经网络水印涉及的相关技术进行介绍;对深度神经网络水印技术进行对比,并重点对白盒和黑盒水印进行详细分析;对神经网络水印攻...     

面向云联网的云服务协商机制

随着云计算的快速发展,越来越多的用户开始使用云服务提供商提供的服务,而云联网作为云计算研究的新领域,可以实现跨云服务提供商的服务,当单个云服务提供商无法满足用户的服务需求时,云服务提供商之间以合作的方式为用户提供服务,以便更好地满足用户的服务需求。针对上述情况,提出了面向云联网的云服务协商机制,该机制利用云联网和改进的经典合同网模型来实现云服务提供商的交互协商。为了有效地选出合作伙伴以提高合作效率,还为每一个云服务提供商建立了一个熟人集。实验表明,本文设计的机制可以有效地提高云服务提供商之间的合作效率,并且可以更好地满足用户的服务需求。     

融合邻域模型与隐语义模型的推荐算法

作为目前构建推荐系统最成功的方法之一,协同过滤算法（CF）是利用已知的一组用户喜好数据来预测用户对其他物品的喜好从而做出个性化推荐的。两种比较成功的协同过滤算法能够直接刻画用户和物品因子的隐语义模型,以及分析物品或者用户之间相似度的邻域模型。提出了一种针对这两种模型的改进方法,使得隐语义模型和邻域模型能够有效结合,从而构建出一个更精确的融合模型。在融合用户的显性反馈与隐性反馈信息对模型进行扩展后,又使得精确度进一步提升。在Netflix数据集上进行测试,实验结果表明,该融合算法在Netflix数据集上的性能优于其他算法。     

Contrastive Meta-learning on Heterogeneous Information Networks for Cold-start Recommendation

In recommender systems, the cold-start issue is challenging due to the lack of interactions between users or items. Such an issue can be alleviated via data-level and model-level strategies. Traditional data-level methods employ auxiliary information like feature information to enhance the learning of user and item embeddings. Recently, Heterogeneous Information Networks (HINs) have been incorporated into the recommender system as they provide more fruitful auxiliary information and meaningful semantics. However, these models are unable to capture the structural and semantic information comprehensively and neglect the unlabeled information of HINs during training. Model-level methods propose to apply the meta-learning framework which naturally fits into the cold-start issue, as it learns the prior knowledge from similar tasks and adapts to new tasks quickly with few labeled samples. Therefore, we propose a contrastive meta-learning framework on HINs named CM-HIN, which addresses the cold-start issue at both data level and model level. In particular, we explore meta-path and network schema views to describe the higher-order and local structural information of HINs. Within meta-path and network schema views, contrastive learning is adopted to mine the unlabeled information of HINs and incorporate these two views. Extensive experiments on three benchmark datasets demonstrate that CM-HIN outperforms all state-of-the-art baselines in three cold-start scenarios.     

Exponential Fuzzy C-Means for Collaborative Filtering

Collaborative filtering(CF) is one of the most popular techniques behind the success of recommendation system.It predicts the interest of users by collecting information from past users who have the same opinions.The most popular approaches used in CF research area are Matrix factorization methods such as SVD.However,many wellknown recommendation systems do not use this method but still stick with Neighborhood models because of simplicity and explainability.There are some concerns that limit neighborhood models to achieve higher prediction accuracy.To address these concerns,we propose a new exponential fuzzy clustering(XFCM) algorithm by reformulating the clustering’s objective function with an exponential equation in order to improve the method for membership assignment.The proposed method assigns data to the clusters by aggressively excluding irrelevant data,which is better than other fuzzy C-means(FCM) variants.The experiments show that XFCM-based CF improved 6.9% over item-based method and 3.0% over SVD in terms of mean absolute error for 100 K and 1 M MovieLens dataset.     

CluCF: a clustering CF algorithm to address data sparsity problem

In QoS-based Web service recommendation, predicting Quality of Service (QoS) for users will greatly aid service selection and discovery. Collaborative filtering (CF) is an effective method for Web service selection and recommendation. Data sparsity is an important challenges for CF algorithms. Although model-based algorithms can address the data sparsity problem, those models are often time-consuming to build and update. Thus, these CF algorithms aren’t fit for highly dynamic and large-scale environments, such as Web service recommendation systems. In order to overcome this drawback, this paper proposes a novel approach CluCF, which employs user clusters and service clusters to address the data sparsity problem and classifies the new user (the new service) by location factor to lower the time complexity of updating clusters. Additionally, in order to improve the prediction accuracy, CluCF employs time factor. Time-aware user-service matrix Mu;s(tk, d) is introduced, and the time-aware similarity measurement and time-aware QoS prediction are employed in this paper. Since the QoS performance of Web services is highly related to invocation time due to some time-varying factors (e.g., service status, network condition), time-aware similarity measurement and time-aware QoS prediction are more trustworthy than traditional similarity measurement and QoS prediction, respectively. Since similarity measurement and QoS prediction are two key steps of neighborhood-based CF, time-aware CF will be more accurate than traditional CF. Moreover, our approach systematically combines user-based and item-based methods and employs influence weights to balance these two predicted values, automatically. To validate our algorithm, this paper conducts a series of large-scale experiments based on a real-world Web service QoS dataset. Experimental results show that our approach is capable of alleviating the data sparsity problem.