Trust-aware recommendation for improving aggregate diversity

Recommender systems are becoming increasingly important and prevalent because of the ability of solving information overload. In recent years, researchers are paying increasing attention to aggregate diversity as a key metric beyond accuracy, because improving aggregate recommendation diversity may increase long tails and sales diversity. Trust is often used to improve recommendation accuracy. However, how to utilize trust to improve aggregate recommendation diversity is unexplored. In this paper, we focus on solving this problem and propose a novel trust-aware recommendation method by incorporating time factor into similarity computation. The rationale underlying the proposed method is that, trustees with later creation time of trust relation can bring more diverse items to recommend to their trustors than other trustees with earlier creation time of trust relation. Through relevant experiments on publicly available dataset, we demonstrate that the proposed method outperforms the baseline method in terms of aggregate diversity while maintaining almost the same recall.     

推荐系统中的新颖性问题研究

准确性推荐中存在商品类型单一、流行商品多、缺乏新意的问题,因而新颖性推荐得到重视。但已有研究在设计算法时未考虑项的特征,无法针对不同用户帮其区分和挑选具备较高新颖度的项。为提高推荐系统的性能,对基于随机游走的方法进行改进,提出融合新颖性特征的推荐算法。从兴趣扩展和预测角度分析项的特征,给出完善的新颖度定义,并结合用户需求构建新的转移概率,产生个性化的推荐列表,提高了列表内容的新意。实验结果表明,提出的算法较现有算法对准确率影响较小,同时在新颖性指标上有明显提升,并得出通过融合新颖性特征能够在兼顾准确性的情况下有效改善推荐内容的结论。     

基于新颖性和多样性的旅游推荐模型研究

人们在旅游活动中经常会利用推荐系统,比如推荐路线、推荐酒店等等,然而这种推荐多数是基于Top-N的热门项目推荐,经常导致游客得到一些信息量为0的“精准推荐”。针对传统的推荐算法过于强调推荐的精准度导致推荐列表的新颖性和多样性差的问题,将MMR技术应用在旅游推荐领域,同时加入用户-项目交互因子,提出一种基于发现的用户项目关系推荐模型,并在真实的数据集上进行测试,通过实验结果,和传统的KNN以及改进前的基于MMR经典算法对比,有效提高了推荐列表的新颖性和多样性。在旅游推荐这种新颖性较高的应用领域,该算法相对于传统的推荐算法具有较大的优势。     

一种基于整体多样性增强的推荐算法

目前大多数推荐算法都是以提高用户对未知商品的预测评分值为主要目标,然而预测准确率并不是增加用户满意度的唯一标准,推荐列表的多样性也是衡量推荐质量的一个重要指标。提出了一种新的推荐方法,旨在提高系统的整体多样性和长尾商品的推荐率。算法综合考虑了商品预测值、商品流行度、商品的偏爱度等多个标准。实验表明,与其他方法相比,本方法在维持较高推荐准确率的同时,能够推荐更多的长尾商品,提高了系统的整体多样性。     

Effective methods for increasing aggregate diversity in recommender systems

In order to make a recommendation, a recommender system typically first predicts a user’s ratings for items and then recommends a list of items to the user which have high predicted ratings. Quality of predictions is measured by accuracy, that is, how close the predicted ratings are to actual ratings. On the other hand, quality of recommendation lists is evaluated from more than one perspective. Since accuracy of predicted ratings is not enough for customer satisfaction, metrics such as novelty, serendipity, and diversity are also used to measure the quality of the recommendation lists. Aggregate diversity is one of these metrics which measures the diversity of items across the recommendation lists of all users. Increasing aggregate diversity is important because it leads a more even distribution of items in the recommendation lists which prevents the long-tail problem. In this study, we propose two novel methods to increase aggregate diversity of a recommender system. The first method is a reranking approach which takes a ranked list of recommendations of a user and reranks it to increase aggregate diversity. While the reranking approach is applied after model generation as a wrapper the second method is applied in model generation phase which has the advantage of being more efficient in the generation of recommendation lists. We compare our methods with the well-known methods in the field and show the superiority of our methods using real-world datasets.     

基于二分图网络的总体多样性增强推荐算法

针对传统推荐算法过于强调推荐准确率而造成推荐系统“长尾”现象加剧问题,提出一种基于二分图网络的总体多样性增强推荐算法。首先,利用现有推荐算法生成的预测评分构建用户候选推荐列表,进而构建二分图网络模型。其次,设定项目容量对热门项目的推荐次数予以限制。最后,结合推荐增广路生成最终推荐列表。与现有的推荐多样性增强算法在真实电影评分数据集上进行实验对比。实验结果表明,本文算法在保证推荐准确率的同时能有效提高推荐的总体多样性。     

Resource recommendation in social annotation systems: A linear-weighted hybrid approach

Social annotation systems enable the organization of online resources with user-defined keywords. Collectively these annotations provide a rich information space in which users can discover resources, organize and share their finds, and connect to other users with similar interests. However, the size and complexity of these systems can lead to information overload and reduced utility for users. For these reasons, researchers have sought to apply the techniques of recommender systems to deliver personalized views of social annotation systems. To date, most efforts have concentrated on the problem of tag recommendation – personalized suggestions for possible annotations. Resource recommendation has not received the same systematic evaluation, in part because the task is inherently more complex. In this article, we provide a general formulation for the problem of resource recommendation in social annotation systems that captures these variants, and we evaluate two cases: basic resource recommendation and tag-specific resource recommendation. We also propose a linear-weighted hybrid framework for resource recommendation. Using six real-world datasets, we show that its integrative approach is essential for this recommendation task and provides the most adaptability given the varying data characteristics in different social annotation systems. We find that our algorithm is more effective than other more mathematically-complex techniques and has the additional advantages of flexibility and extensibility.     

Clustering-based diversity improvement in top-N recommendation

The major aim of recommender algorithms has been to predict accurately the rating value of items. However, it has been recognized that accurate prediction of rating values is not the only requirement for achieving user satisfaction. One other requirement, which has gained importance recently, is the diversity of recommendation lists. Being able to recommend a diverse set of items is important for user satisfaction since it gives the user a richer set of items to choose from and increases the chance of discovering new items. In this study, we propose a novel method which can be used to give each user an option to adjust the diversity levels of their own recommendation lists. Experiments show that the method effectively increases the diversity levels of recommendation lists with little decrease in accuracy. Compared to the existing methods, the proposed method, while achieving similar diversification performance, has a very low computational time complexity, which makes it highly scalable and allows it to be used in the online phase of the recommendation process.     

知识表示学习研究进展

新型深度学习推荐模型已广泛应用至现代推荐系统,其独有的特征——包含万亿嵌入参数的嵌入层,带来的大量不规则稀疏访问已成为模型预估的性能瓶颈. 然而,现有的推荐模型预估系统依赖CPU对内存、外存等存储资源上的嵌入参数进行访问,存在着CPU-GPU通信开销大和额外的内存拷贝2个问题,这增加了嵌入层的访存延迟,进而损害模型预估的性能. 提出了一种基于GPU直访存储架构的推荐模型预估系统GDRec.GDRec的核心思想是在嵌入参数的访问路径上移除CPU参与,由GPU通过零拷贝的方式高效直访内外存资源. 对于内存直访,GDRec利用统一计算设备架构（compute unified device architecture,CUDA）提供的统一虚拟地址特性,实现GPU 核心函数（kernel）对主机内存的细粒度访问,并引入访问合并与访问对齐2个机制充分优化访存性能;对于外存直访,GDRec实现了一个轻量的固态硬盘（solid state disk,SSD）驱动程序,允许GPU从SSD中直接读取数据至显存,避免内存上的额外拷贝,GDRec还利用GPU的并行性缩短提交I/O请求的时间. 在3个点击率预估数据集上的实验表明,GDRec在性能上优于高度优化后的基于CPU访存架构的系统NVIDIA HugeCTR,可以提升多达1.9倍的吞吐量.

     

基于位置的社会化网络的并行化推荐算法

针对传统的协同过滤算法在利用签到记录进行兴趣点(POI)推荐时不能充分利用签到信息所隐含的偏好、位置和社交网络信息而损失准确率的问题,以及传统的单机串行算法在大数据处理能力上的弱势,提出一种基于位置和朋友关系的协同过滤(LFBCF)算法,以用户历史偏好为基础,综合考虑用户社交关系网络进行协同过滤,并以用户的活动范围作为约束实现对用户的兴趣点推荐。为了支持大数据量的实验,将算法在Spark分布式计算平台上进行了并行化实现。研究过程中使用了Gowalla和Brightkite这两个基于位置的社会化网络数据集,分析了数据集中签到数量、签到位置之间距离、社交关系等可能对推荐结果造成影响的因素,以此来支持提出的算法。实验部分通过与传统的协同过滤算法等经典算法在准确率、F-measure上的对比验证了算法在推荐效果上的优越性,并通过并行算法与单机串行算法在不同数据规模上加速比的对比验证了算法并行化的意义以及性能上的优越性。     

Eye-tracking and social behavior preference-based recommendation system

The Journal of Supercomputing - With the popularization of wireless Internet technology and smartphones, the importance of recommendation systems, which analyze personality of a user using social...     

基于位置社交网络的个性化兴趣点推荐

兴趣点(point-of-interest,POI)推荐是基于位置的社交网络(location-based social networks,LBSN)中一项重要的服务。针对目前推荐算法存在的噪声数据影响推荐质量,用户个性化程度低的问题,提出了一种个性化联合推荐算法。提出了引入POI的位置因素去除不可能或可能性较小的POI,形成初步候选集;综合考虑POI的类别、流行度及用户的社会行为,增加用户个性化的程度,提高推荐结果的质量。在Foursquare真实签到数据集上的实验,证明了提出的联合推荐算法与目前先进的算法相比,准确率提高11%,召回率提高8%。     

多维加权社会网络中的个性化推荐算法

个性化推荐是解决Internet中信息过载的重要工具,在研究有关个性化推荐的技术和相关动态的基础上,以用户实际应用为驱动,提出一种多维加权社会网络中的个性化推荐算法。首先,该算法构建了用户之间的多维加权网络;然后利用复杂网络的聚类方法——CPM算法寻找邻居用户;最后基于用户之间的相似性做出推荐。实验结果表明,应用该算法的多维网络的推荐系统与基于内容推荐系统和协同过滤推荐系统相比,有较高的查全率和准确率,个性化推荐质量有了一定程度的提高。     

电子商务推荐系统中推荐策略的自适应性

针对电子商务推荐系统中各种推荐技术的不足,提出推荐策略的自适应方法。用二元组《用户知识,推荐商品》代表推荐环境的根本特征．采用ART神经网络进行自学习,获取推荐环境的不同聚类。每个聚类代表了某种推荐环境,对推荐结果的反馈情况进行统计分析．确定每个聚类的最佳推荐技术。向用户推荐商品时,根据用户所在聚类采用具有最佳推荐质量的推荐技术向用户作出推荐。整个系统的工作过程不需要人工干预,具有自适应性。     

Hybrid followee recommendation in microblogging systems

Bug reports are widely employed to facilitate software tasks in software maintenance. Since bug reports are contributed by people, the authorship characteristics of contributors may heavily impact the perfor-mance of resolving software tasks. Poorly written bug reports may delay developers when fixing bugs. However, no in-depth investigation has been conducted over the authorship characteristics. In this study, we first leverage byte-level N-grams to model the authorship characteristics and employ Normalized Simplified Profile Intersection (NSPI) to identify the similarity of the authorship characteristics. Then, we investigate a series of properties related to contributors’ authorship characteristics, including the evolvement over time and the variation among distinct products in open source projects. Moreover, we show how to leverage the authorship characteristics to facilitate a well-known task in software maintenance, namely Bug Report Summarization (BRS). Experiments on open source projects validate that incorporating the authorship characteristics can effectively improve a state-of-the-art method in BRS. Our findings suggest that contributors should retain stable authorship characteristics and the authorship characteristics can assist in resolving software tasks.

     

一种社会化标注系统资源个性化推荐方法

目前许多基于社化化标注的个性化资源推荐方法均忽视了用户长短期兴趣和多义标签问题对推荐的不同影响,为此,设计区分用户长短期兴趣的指标——用户的标签偏好权重和资源偏好权重;在此基础上,提出一种结合基于内容和基于协同过滤方法优点的混合推荐方法,通过加入标注相同资源的标签向量相似度计算因子,来减小多义标签对推荐结果的影响。实验表明,将该方法引入社会化标注系统资源个性化推荐算法中,能提高推荐精度。     

学术社交网络中的权威学者推荐模型

目前，学术社交网络平台存在的信息过载和信息不对称等问题导致学者特别是影响力低的学者很难找到自己感兴趣的内容，同时，学术社交网络中影响力大的学者对学术社区的形成具有一定的促进作用并且对影响力低的学者的科学研究具有一定的导向作用，因此提出一种融合学术社区检测的权威学者推荐模型（ISRMACD）来为学术社交网络中的低影响力学者提供推荐服务。首先，利用影响力大的学者圈作为社区的核心结构对学术社交网络中学者间的关系纽带——好友关系所产生的复杂网络拓扑关系进行学术社区检测；然后，对社区内的学者计算影响力，并实现社区内部的权威学者推荐服务。在学者网数据集上的实验结果表明，该推荐模型在不同的权威学者推荐数量下均取得了较高的推荐质量，并且每次推荐10名权威学者取得的推荐精度最高，达到70%及以上。     

融合社交网络和图像内容的兴趣点推荐

基于位置的社交网络（LBSN）蓬勃发展，带来了大量的兴趣点（POI）数据，加速了兴趣点推荐的研究。针对用户-兴趣点矩阵极端稀疏造成的推荐精度低和兴趣点特征缺失问题，通过融合兴趣点的标签、地理、社交、评分以及图像等信息，提出了一种融合社交网络和图像内容的兴趣点推荐方法（SVPOI）。首先分析兴趣点数据集，针对地理信息，利用幂律概率分布构造距离因子；针对标签信息，利用检索词频率构造标签因子；融合已有的历史评分数据，构造新的用户-兴趣点评分矩阵。其次利用VGG16深度卷积神经网络模型（DCNN）识别兴趣点图像内容，构造兴趣点图像内容矩阵。然后根据兴趣点数据的社交网络信息，构造用户社交矩阵。最后，利用概率矩阵分解（PMF）模型，融合用户-兴趣点评分矩阵、图像内容矩阵、用户社交矩阵，构成SVPOI兴趣点推荐模型，生成兴趣点推荐列表。大量的真实数据集上的实验结果表明，与PMF、SoRec、TrustMF、TrustSVD推荐算法相比，SVPOI推荐的准确度均有较大提升，其平均绝对误差（MAE）和均方根误差（RMSE）两项指标比最优的TrustMF算法分别降低了5.5%和7.82%，表明SVPOI具有更好的推荐效果。