Topic-tracking-based dynamic user modeling with TV recommendation applications

One of the challenging issues in TV recommendation applications based on implicit rating data is how to make robust recommendation for the users who irregularly watch TV programs and for the users who have their time-varying preferences on watching TV programs. To achieve the robust recommendation for such users, it is important to capture dynamic behaviors of user preference on watched TV programs over time. In this paper, we propose a topic tracking based dynamic user model (TDUM) that extends the previous multi-scale dynamic topic model (MDTM) by incorporating topic-tracking into dynamic user modeling. In the proposed TDUM, the prior of the current user preference is estimated as a weighted combination of the previously learned preferences of a TV user in multi-time spans where the optimal weight set is found in the sense of the evidence maximization of the Bayesian probability. So, the proposed TDUM supports the dynamics of public users’ preferences on TV programs for collaborative filtering based TV program recommendation and the highly ranked TV programs by similar watching taste user group (topic) can be traced with the same topic labels epoch by epoch. We also propose a rank model for TV program recommendation. In order to verify the effectiveness of the proposed TDUM and rank model, we use a real data set of the TV programs watched by 1,999 TV users for 7 months. The experiment results demonstrate that the proposed TDUM outperforms the Latent Dirichlet Allocation (LDA) model and the MDTM in log-likelihood for the topic modeling performance, and also shows its superiority compared to LDA, MDTM and Bayesian Personalized Rank Matrix Factorization (BPRMF) for TV program recommendation performance in terms of top-N precision-recall.     

联合学习用户端和项目端知识图谱的个性化推荐

如何在已有的用户行为和辅助信息的基础上准确建模用户的偏好非常重要。在各种辅助信息中,知识图谱(Know-ledge Graph,KG)作为一种新型辅助信息,其节点和边包含了丰富的结构信息和语义信息,近年来受到了越来越多研究者的关注。大量研究表明,在个性化推荐中引入知识图谱可以有效地提高推荐的性能,并增强推荐的合理性和可解释性。然而,现有的方法要么是在KG上探索每个用户-项目交互对(user-item)的独立子路径,要么使用图表示学习的方法在KG中分别学习目标用户(user)或项目(item)的表示,虽然都取得了一定的效果,但是前者没有充分捕获用户-项目(user-item)在KG上的结构信息,后者在产生嵌入(embedding)表示的过程中忽略了user和item的相互影响。为了弥补上述方法的不足,提出了一种联合学习用户端和项目端知识图谱(User-end and Item-end Knowledge Graph,UIKG)的新模型。该模型通过挖掘用户和项目在各自KG中的关联属性信息,并通过联合学习有效地捕获用户的个性化偏好与项目之间的关联性。具体的操作步骤是,利用基于图卷积神经网络的方法从用户知识图谱中学习用户表示向量,再将用户表示向量引入项目知识图谱中联合学习得到项目表示向量,实现用户端KG和项目端KG的无缝统一,最后通过多层感知器进行偏好预测,得到用户对项目的偏好概率,从而更有效地挖掘KG中的高阶结构信息和语义信息来捕获用户的个性化偏好。在公开数据集上的实验结果表明,与基线方法相比,UIKG在Recall@K指标上提高了2.5%~13.6%,在AUC和F1指标上提高了0.4%~5.8%。     

3PRS: a personalized popular program recommendation system for digital TV for P2P social networks

Digital TV channels require users to spend more time to choose their favorite TV programs. Electronic Program Guides (EPG) cannot be used to find popular TV programs. Hence, this paper proposes a personalized Digital Video Broadcasting — Terrestrial(DVB-T) Digital TV program recommendation system for P2P social networks. From the DVB-T signal, we obtain EPG of TV programs. The frequency and duration of the programs that users have watched are used to extract programs that users are interested in. The information is collected and weighted by Information Retrieval (IR). The program information is then clustered by k-means. Clusters of users are also grouped by k-means to find cluster relationships. In each group, we decide the most popular program in the group according to the program weight of the channel. When a new user begins to watch the TV program, the K-Nearest Neighbor (kNN) classification method is used to determine the user’s predicted cluster label. Then, our system recommends popular programs in the predicted cluster and similar clusters.     

Neural Explainable Recommender Model Based on Attributes and Reviews

Explainable recommendation, which can provide reasonable explanations for recommendations, is increasingly important in many fields. Although traditional embedding-based models can learn many implicit features, resulting in good performance, they cannot provide the reason for their recommendations. Existing explainable recommender methods can be mainly divided into two types. The first type models highlight reviews written by users to provide an explanation. For the second type, attribute information is taken into consideration. These approaches only consider one aspect and do not make the best use of the existing information. In this paper, we propose a novel neural explainable recommender model based on attributes and reviews (NERAR) for recommendation that combines the processing of attribute features and review features. We employ a tree-based model to extract and learn attribute features from auxiliary information, and then we use a time-aware gated recurrent unit (T-GRU) to model user review features and process item review features based on a convolutional neural network (CNN). Extensive experiments on Amazon datasets demonstrate that our model outperforms the state-of-the-art recommendation models in accuracy of recommendations. The presented examples also show that our model can offer more reasonable explanations. Crowd-sourcing based evaluations are conducted to verify our model’s superiority in explainability.

     

A hybrid content-based and item-based collaborative filtering approach to recommend TV programs enhanced with singular value decomposition

With the advent of new cable and satellite services, and the next generation of digital TV systems, people are faced with an unprecedented level of program choice. This often means that viewers receive much more information than they can actually manage, which may lead them to believe that they are missing programs that could likely interest them. In this context, TV program recommendation systems allow us to cope with this problem by automatically matching user’s likes to TV programs and recommending the ones with higher user preference.This paper describes the design, development, and startup of queveo.tv: a Web 2.0 TV program recommendation system. The proposed hybrid approach (which combines content-filtering techniques with those based on collaborative filtering) also provides all typical advantages of any social network, such as supporting communication among users as well as allowing users to add and tag contents, rate and comment the items, etc. To eliminate the most serious limitations of collaborative filtering, we have resorted to a well-known matrix factorization technique in the implementation of the item-based collaborative filtering algorithm, which has shown a good behavior in the TV domain. Every step in the development of this application was taken keeping always in mind the main goal: to simplify as much as possible the user task of selecting what program to watch on TV.     

融合画像和文本信息的轻量级关系图注意推荐模型

针对当前基于图神经网络的推荐系统受数据稀疏影响推荐效率不高的问题,提出融合画像和文本信息的轻量级关系图注意推荐模型(LightRGAN)。首先,利用用户画像和项目画像初始化用户和项目的嵌入表示。其次,引入评论、项目描述和项目类型作为辅助信息,并通过基于多头注意力机制的文本嵌入网络挖掘同一用户评论集和描述集中文本之间的潜在联系。然后,通过融合注意力机制的轻量级关系图卷积网络学习用户和项目的嵌入表示。最后,对各层嵌入表示加权求和并通过预测网络计算匹配分数。在三个公开数据集上的实验结果表明LightRGAN的效果优于多个现有的基线模型,评估指标HR@20、NDCG@20较最优基线模型最少提升了2.58%、2.37%。     

融合用户偏好和多交互网络的协同过滤算法

推荐系统中的辅助信息可以为推荐提供有用的帮助,而传统的协同过滤算法在计算用户相似度时对辅助信息的利用率低,数据稀疏性大,导致推荐的精度偏低.针对这一问题,本文提出了一种融合用户偏好和多交互网络的协同过滤算法(NIAP-CF).该算法首先根据评分矩阵和项目属性特征矩阵挖掘出用户的项目属性偏好信息,然后使用SBM方法计算用户间的项目属性偏好相似度,并用其改进用户相似度计算公式.在进行评分预测时,构建融合用户-项目属性偏好信息的多交互神经网络预测模型,使用动态权衡参数综合由用户相似度计算出的预测评分和模型的预测评分来进行项目推荐.本文使用MovieLens数据集进行实验验证,实验结果表明改进算法能够提高推荐的精度,降低评分预测的MAE和RMSE值.     

融合用户社交关系的自适应图卷积推荐算法

为了缓解推荐系统中不同用户社交空间与兴趣空间的内在信息差异和忽视高阶邻居的问题,提出了一种融合用户社交关系的自适应图卷积推荐算法（adaptive graph convolutional recommendation algorithm integrating user social relationships,AGCRSR）。首先,模型在嵌入层使用映射矩阵将初始特征向量转换为自适应嵌入;其次,引入注意力机制聚合不同方面的用户嵌入,通过图卷积网络来线性学习用户和项目的潜在表示;最后,通过自适应模块聚合用户表示并利用内积函数预测用户对项目的最终推荐结果。在数据集LastFM和Ciao上与其他基线算法进行了对比实验,实验结果表明AGCRSR的推荐效果较其他算法有显著提升。     

图神经网络会话推荐系统综述

会话推荐立足于目标用户的当前会话,根据项目类别、跨会话的上下文信息、多种用户行为等辅助信息学习项目间的依赖关系,从而捕捉用户的长短期偏好进行个性化推荐。近年来,流行的深度学习系列方法已经成为会话型推荐系统这个研究热点的前沿方法,尤其是图神经网络的引入,使会话推荐系统的性能得到了进一步提升。鉴于此,该综述从问题定义与会话推荐因素出发,从构图方面进行分析;将相关工作分为基于图卷积网络、门控图神经网络、图注意力网络和其他图神经网络架构的会话推荐系统,并进行归纳与对比;对各工作实验部分中的损失函数类别、所选用的数据集和模型性能评估指标三方面进行深入分析。重点从算法原理和性能分析两方面对各模型框架进行评估和梳理,旨在对近五年基于图神经网络的会话推荐系统相关工作进行评述、总结与展望。     

Automatic and personalized recommendation of TV program contents using sequential pattern mining for smart TV user interaction

Due to the excessive number of TV program contents available at user’s side, efficient access to the preferred TV program content becomes a critical issue for smart TV user interaction. In this paper, we propose an automatic recommendation scheme of TV program contents in sequence using sequential pattern mining (SPM). Motivation of sequential TV program recommendation is based on TV viewer’s behaviors for watching multiple TV program contents in a row. A sequence of TV program contents for recommendation to a target user is constructed based on the features such as an occurrence and net occurrence of frequently watched TV program contents from the similar user group to which the target user belongs. Three types of SPM methods are presented—offline, online and hybrid SPM. To extract sequential patterns of preferably watched TV program contents, we propose a preference weighted normalized modified retrieval rank (PW-NMRR) metric for similar user clustering. In the offline SPM method, we effectively construct the sequential patterns for recommendation using a projection method, which yields good performance for relatively longer sequential patterns. The online SPM method mines sequential patterns online by effectively reflecting the recent preference characteristics of users for TV program contents, which is effective for short-sequence recommendation. The hybrid SPM method combines the offline and online SPM methods. The maximum precisions of 0.877, 0.793 and 0.619 for length-1, -2 and -3 sequence recommendations are obtained from the online, hybrid and offline SPM methods, respectively.     

PCC:一个对单用户建模的个性化对话系统

对话系统是自然语言处理(NLP)领域中一个重要的下游任务,在近几年得到了越来越多的关注,并取得了很大的发展.然而尽管对话领域已经取得了许多优秀的成果,现有的对话模型在拓展个性化方面依然有很大的局限性.为了使对话模型更符合人类的对话方式,拥有更好的个性化建模能力,该文提出一种新的对单个用户建模的个性化模型PCC(a Pe...     

基于用户-项目交叉注意力机制的迁移推荐模型

随着互联网技术的发展,个性化的推荐系统得到了广泛应用.但用户数据稀疏与冷启动仍是推荐系统普遍面临的难题.将深度学习与注意力机制相结合,提出基于用户-项目交叉注意力机制的迁移推荐模型.该模型能够充分学习源域数据中用户、物品及评分间的潜在关系,然后初始化目标域神经网络,迁移应用到目标域.为验证算法模型的有效性,在公开数据集...     

基于知识图谱上下文的图注意矩阵补全

针对图卷积编码器提取用户、项目信息过程中权重共享,不能区分邻域之间重要性,以及知识图谱作为辅助信息时,基于图神经网络方法无法显示对知识图谱非本地上下文（最相关的高阶邻居集合）信息进行捕获的问题,提出一种基于双向交互图传递的图注意编码器框架,显示利用知识图谱本地（一阶邻居集合）和非本地上下文信息。通过图注意编码器获取用户、项目的嵌入向量;考虑用户对实体的个性化偏好,通过特定于用户的图注意机制来捕获知识图的本地上下文信息;使用随机游走抽样提取实体的非本地上下文,并使用递归神经网络建模实体与非本地上下文实体之间的依赖关系,通过一个双线性解码器重建二部图中的链接。与现有的方法相比,在真实数据集上的实验结果验证了该模型的优越性。     

协同过滤推荐系统综述

随着互联网和信息计算的飞速发展,衍生了海量数据,我们已经进入信息爆炸的时代。网络中各种信息量的指数型增长导致用户想要从大量信息中找到自己需要的信息变得越来越困难,信息过载问题日益突出。推荐系统在缓解信息过载问题中起着非常重要的作用,该方法通过研究用户的兴趣偏好进行个性化计算,由系统发现用户兴趣进而引导用户发现自己的信息需求。目前,推荐系统已经成为产业界和学术界关注、研究的热点问题,应用领域十分广泛。在电子商务、会话推荐、文章推荐、智慧医疗等多个领域都有所应用。传统的推荐算法主要包括基于内容的推荐、协同过滤推荐以及混合推荐。其中,协同过滤推荐是推荐系统中应用最广泛最成功的技术之一。该方法利用用户或物品间的相似度以及历史行为数据对目标用户进行推荐,因此存在用户冷启动和项目冷启动问题。此外,随着信息量的急剧增长,传统协同过滤推荐系统面对数据的快速增长会遇到严重的数据稀疏性问题以及可扩展性问题。为了缓解甚至解决这些问题,推荐系统研究人员进行了大量的工作。近年来,为了提高推荐效果、提升用户满意度,学者们开始关注推荐系统的多样性问题以及可解释性等问题。由于深度学习方法可以通过发现数据中用户和项目之间的非线性关系从而学习一个有效的特征表示,因此越来越受到推荐系统研究人员的关注。目前的工作主要是利用评分数据、社交网络信息以及其他领域信息等辅助信息,结合深度学习、数据挖掘等技术提高推荐效果、提升用户满意度。对此,本文首先对推荐系统以及传统推荐算法进行概述,然后重点介绍协同过滤推荐算法的相关工作。包括协同过滤推荐算法的任务、评价指标、常用数据集以及学者们在解决协同过滤算法存在的问题时所做的工作以及努力。最后提出未来的几个可研究方向。     

融合知识图谱与注意力机制的推荐算法

为了解决信息过载问题,提出了一种融合知识图谱与注意力机制的推荐模型.在该模型中,将知识图谱作为辅助信息进行嵌入,可以缓解传统推荐算法数据稀疏和冷启动问题,并且给推荐结果带来可解释性.为了提升推荐准确率以及捕捉用户兴趣的动态变化,再结合深度学习中的神经网络以及注意力机制生成用户自适应表示,加上动态因子来更好地捕捉用户动态...     

基于知识图谱的金融新闻个性化推荐算法

个性化新闻资讯推荐能够有效地捕捉用户兴趣,提供高质量推荐服务的能力,因而吸引了大量高黏性用户,而知识图谱则以"实体-关系-实体"的形式表示事物间的关系,通过知识图谱中实体间的关系学习到更丰富的特征及语义信息.为更好地实现金融领域新闻的个性化推荐,提出一种基于知识图谱的个性化推荐算法KHA-CNN.结合金融业知识图谱,采...     

Flickr group recommendation with auxiliary information in heterogeneous information networks

Over the past few years, the appropriate utilization of user communities or image groups in social networks (i.e., Flickr or Facebook) has drawn a great deal of attention. In this paper, we are particularly interested in recommending preferred groups to users who may favor according to auxiliary information. In real world, the images captured by mobile equipments explicitly record a lot of contextual information (e.g., locations) about users generating images. Meanwhile, several words are employed to describe the particular theme of each group (e.g., “Dogs for Fun Photos” image group in Flickr), and the words may mention particular entities as well as their belonging categories (e.g., “Animal”). In fact, the group recommendation can be conducted in heterogeneous information networks, where informative cues are in general multi-typed. Motivated by the assumption that the auxiliary information (visual features of images, mobile contextual information and entity-category information of groups in this paper) in heterogeneous information networks will boost the performance of the group recommendation, this paper proposes to combine auxiliary information with implicit user feedback for group recommendation. In general, the group recommendation in this paper is formulated as a non-negative matrix factorization (NMF) method regularized with user–user similarity via visual features and heterogeneous information networks. Experiments show that our proposed approach outperforms other counterpart recommendation approaches.     

基于注意力机制的协同卷积动态推荐网络

一直以来, 各种推荐系统关注于如何挖掘用户与物品特征间的潜在关联, 特征信息的充分利用有利于用户到物品的精准匹配. 基于矩阵分解和分解机的推荐算法是该领域的主流, 前者学习用户历史行为而后者分析对象特征关系, 但都难以兼顾用户行为与个体特征. 而近年来, 深度神经网络凭借其强大的特征学习能力和灵活可变的结构被应用到了推荐系统领域. 鉴于此, 本文提出了一种基于注意力机制的协同卷积动态推荐网络(Attentionbased collaborative convolutional dynamic network, ACCDN), 它通过注意力机制实现用户历史行为、用户画像与物品属性的多重交互, 再通过卷积网络逐层捕捉更高阶的特征交互. 网络同时接受不同组块输出的低阶至高阶信息, 最后给出用户对指定物品青睐评分概率的预估. 而且本文还提出了一种基于无参时间衰减的用户兴趣标签来量化用户关注的变化. 通过比较若干先进模型在两个现实数据集的表现, 本文设计的动态推荐模型不但能够缓解推荐时滞性, 还能明显提高推荐质量, 为用户带来更好的个性化服务体验.     

融合了LSTM和PMF的推荐算法

推荐系统是帮助用户在海量的数据中快速发掘出他们感兴趣内容的最重要的技术之一。稀疏性和冷启动是推荐系统面临的主要问题。针对稀疏性问题,已有多种推荐算法考虑利用额外的辅助信息,如评论、摘要或概要等来提高预测准确性。这些算法确实已经在一定程度上提高了预测准确性,但是,已有的算法大都是基于词袋模型,对这些辅助信息的理解和利用缺乏深度,留于表面。提出了一种新型的推荐系统算法：深度协同过滤算法（DCF）。DCF集成了长短期记忆网络（LSTM）和概率矩阵分解（PMF）。该算法不仅能够基于用户评分学习用户特征,而且能深度挖掘辅助信息,学习到更精确的物品特征。经过在真实数据集MovieLens100K和1M上的验证,结果表明DCF算法的根均方误差比现有算法分别降低了2.54%和3.96%。     

Path-enhanced explainable recommendation with knowledge graphs

Recommender systems, which are used to predict user requirements precisely, play a vital role in the modern internet industry. As an effective tool with rich semantics, knowledge graphs have recently attracted growing research attention in enhancing recommendation results. By mining multihop relations (i.e., paths) between user-item interactions within a knowledge graph, implicit user preferences and other side information can be clearly revealed. Nevertheless, existing knowledge graph-based recommendation methods have two fundamental limitations. First, the indiscriminate utilization of user-item path sets conveys unclear information and negatively influences explainability. Moreover, obtaining reliable recommendation results with these methods requires large amounts of prior knowledge, which indicates that they show poor performance in terms of accuracy and handling cold-start issues. To address these issues, we propose a novel model called the Path-enhanced Recurrent Network (PeRN). Specifically, PeRN integrates a recurrent neural network encoder with a metapath-based entropy encoder to increase explainability and accuracy and reduce cold-start costs. The recurrent network encoder has a strong ability to represent sequential path semantics in a knowledge graph, while the entropy encoder, as an efficient statistical analysis tool, leverages metapath information to differentiate paths in a single user-item interaction. A path extraction algorithm with a bidirectional scheme is also proposed to make PeRN more feasible. The experimental results on two real-world datasets demonstrate our significant improvements with reasonable explanations, promising accuracy and a minimal amount of prior knowledge compared with several state-of-the-art baselines.