下一个购物篮推荐系统算法研究

下一个购物篮推荐旨在为用户推荐下一次想购买的商品,与传统推荐不同,它考虑了商品间的时序相关性,购物篮中的商品可能相互依赖,而非彼此独立。如何更好地挖掘用户的时序行为特征是下一个购物篮推荐的难点和挑战。该文首先阐述了下一个购物篮推荐的内涵及研究意义,并对它做基本介绍。然后重点梳理了下一个购物篮推荐的研究进展,对其算法整理分析,阐述每种方法的优势和不足,并贯穿了其算法的发展情况、存在问题和研究现状。最后对下一个购物篮推荐的发展进行展望,为后续研究提供参考。     

基于图注意力网络的下一个购物篮推荐

购物篮是用户在一次购物中一系列物品的集合。在下一个购物篮推荐中，可以根据用户的历史购物篮序列推荐出用户接下来购买的物品集合。受图注意力网络的启发，利用该网络建模购物篮中的物品联系，得到含有物品关系的购物篮表示；为了建模用户的短期兴趣，设计一个固定大小的移动窗口，融合最近几个连续购物篮的用户偏好；融合经过循环神经网络的篮子表示、全局和短期的用户购物偏好得到最终的推荐。在两个公开数据集上进行实验，结果表明该算法可有效提高下一个购物篮推荐精度。     

基于改进CNN的局部相似性预测推荐模型

为缓解推荐系统中数据稀疏性问题,利用卷积神经网络CNN具有较强捕捉局部特征能力的优势,通过加入一个调节层,提出一种改进CNN的局部相似性预测推荐模型LSPCNN。新模型对初始用户-项目评分矩阵进行迭代调整,使用户兴趣偏好局部特征化,再融合CNN对缺失评分进行预测,从而实施个性化推荐。实验结果表明,LSPCNN模型在不同数据稀疏度下的MAE值较传统推荐方法平均下降4%,有效缓解了数据稀疏性,提高了推荐系统的性能。     

用于个性化推荐的条件卷积隐因子模型

在推荐系统中,传统的矩阵分解无法提取用户和物品特征,而神经协同过滤(NCF)在分解模型中增加多层感知器,但不能有效利用用户和物品ID之外的辅助信息.为此,提出一种新的条件卷积方法.通过将物品特征作为输入,将用户特征作为卷积核,达到权值不共享的目的,使得条件卷积具有更强的特征提取和组合能力以及不增加参数量的特性.在此基础上,条件卷积能够融入多种辅助信息进行个性化推荐.实验结果表明,与NCF模型相比,该方法在隐性反馈数据中推荐命中率提升3.11%,在显性反馈数据中评分预测误差降低2.47%.     

基于生成对抗模型的序列推荐算法

针对传统序列推荐算法时间信息和项目内容信息运用不充分的问题,该文提出基于生成对抗模型的序列推荐算法。通过生成对抗模型将序列建模与时间、内容信息建模分离,充分挖掘用户项目交互的序列信息和项目内容信息。运用卷积神经网络作为生成对抗模型的生成器,捕获用户项目交互的序列模式。运用注意力机制作为生成对抗模型的判别器,捕获交互序列的时间信息和项目内容信息。针对传统序列推荐算法时间信息建模不充分的问题,提出一种改进的时间嵌入方式,充分建模用户项目交互关于时间的周期性模式。利用生成对抗模型同时建模用户的稳定偏好和动态偏好,提升推荐系统的用户体验,并在公开数据集MovieLens-1M和Amazon-Beauty上与现有的优秀算法做比较。实验证明,该文所提出的算法在评价指标HR@N和NDCG@N上较基线方法均有一定提升。     

基于用户偏好特征挖掘的个性化推荐算法

为了提升社交网络个性化推荐能力,结合用户行为分布进行个性化推荐设计,文中提出基于用户行为特征挖掘的个性化推荐算法,构建社交网络的用户行为信息特征挖掘模型,采用显著数据分块检测方法对社交网络用户特征的行为信息进行融合处理,提取反映用户偏好的语义信息特征量。从情感、关键词和结构等方面根据用户行为特征组,结合模糊信息感知方法进行社交网络个性化推荐过程中的信息融合处理,在关联规则约束控制下,构建社交网络用户偏好特征的混合推荐模型,实现用户偏好特征挖掘,根据语义分布和用户的行为偏好实现社交网络的个性化信息推荐。仿真结果表明,采用所提方法进行社交网络个性化推荐的特征分辨能力较好,对用户行为特征的准确识别能力较强,提高了社交网络推荐输出的准确性。     

融合显隐式反馈的协同过滤推荐模型

融合显式和隐式反馈已被应用于提升推荐模型的性能,但是,现有的此类推荐模型未能保留显式反馈中反映用户偏好程度的信息,且现有研究认为拥有显式反馈的数据和仅拥有隐式反馈的数据对于模型具有同等影响,未能充分发挥显式反馈的优势.针对这些问题,提出一种新的融合显式和隐式反馈的协同过滤推荐模型(CEICF).首先,所提出模型提取显式反馈中的特征得到用户/物品的全局偏好向量;然后,从隐式反馈中提取用户/物品的潜在向量,进而将两种向量进行融合得到用户/物品的偏好向量;最后,使用神经网络预测用户与物品交互的可能性.在训练模型时,定义一种加权的二进制交叉熵损失函数,加强显式反馈对模型的影响来增强模型捕获用户偏好的能力.为了验证所提出模型的有效性,在覆盖不同领域的现实数据集上进行实验,实验结果表明,CEICF可有效地融合显式和隐式反馈,且推荐效果相对于基线模型有显著提升.     

融合注意力机制的学生退课行为预测

近年来,大规模在线开放课程(MOOCs)发展迅速,吸引了学界的广泛关注.用户退课率极高这一问题的长期存在,使得退课行为预测成为了一个重要的研究课题.目前的退课行为预测模型过于依赖传统的机器学习算法.此外,很多研究忽视了MOOCs用户灵活修课的特点,采用时序无关的方法进行预测.针对目前该领域存在的问题,论文提出了一种融合注意力机制的时序预测模型.该模型首先利用长短期记忆网络从原始的时序数据中学习新的时序隐态表示,再使用多个一维卷积神经网络提取隐态中各类特征的时序模式,最后融合注意力机制,使模型能够通过注意力分布值强化有效特征.实验结果表明,该方法的预测能力优于其他方法.     

基于时间和关系感知的图协同过滤跨域序列推荐

跨域序列推荐旨在从给定的某用户在不同领域中的历史交互序列中挖掘其偏好,预测其在多个领域中最可能与之交互的下一个项目,以缓解数据稀疏对用户意图捕捉和预测的影响.受协同过滤思想启发,提出一种基于时间和关系感知的图协同过滤跨域序列推荐（timeandrelation-awaregraph collaborative filtering for cross-domain sequential recommendation, TRaGCF）算法,充分挖掘用户高阶行为模式同时利用跨域用户行为模式双向迁移,解决序列推荐中的数据稀疏问题.首先,为获得用户行为序列中项目间复杂的时序依赖关系,提出时间感知图注意力（time-aware graph attention, Ta-GAT）学习项目的域间序列级表示;其次,通过域内用户-项目交互二部图挖掘用户的行为偏好,提出关系感知图注意力（relation-aware graph attention, Ra-GAT）学习项目协同表示和用户协同偏好表示,为用户偏好特征的跨域迁移提供基础;最后为同步提高2个领域中的推荐效果,提出用户偏好特征双向迁移模块（user p...     

融合信任隐性影响和信任度的推荐模型

现有一些方法通过结合传统推荐技术和社交信息,缓解推荐系统中的冷启动问题,但由于可用的社交信息较少,效果不佳.因此,文中提出融合信任隐性影响和信任度的推荐模型,在引入社交信息中信任关系的前提下,不仅考虑用户在信任关系中的显式行为数据,还考虑信任关系的隐性影响(如被信任用户的潜在特征向量),用于获取冷启动用户的偏好特征,有...     

An algorithm for efficient privacy-preserving item-based collaborative filtering

Collaborative filtering (CF) methods are widely adopted by existing recommender systems, which can analyze and predict user “ratings” or “preferences” of newly generated items based on user historical behaviors. However, privacy issue arises in this process as sensitive user private data are collected by the recommender server. Recently proposed privacy-preserving collaborative filtering (PPCF) methods, using computation-intensive cryptography techniques or data perturbation techniques are not appropriate in real online services. In this paper, an efficient privacy-preserving item-based collaborative filtering algorithm is proposed, which can protect user privacy during online recommendation process without compromising recommendation accuracy and efficiency. The proposed method is evaluated using the Netflix Prize dataset. Experimental results demonstrate that the proposed method outperforms a randomized perturbation based PPCF solution and a homomorphic encryption based PPCF solution by over 14X and 386X, respectively, in recommendation efficiency while achieving similar or even better recommendation accuracy.     

Illuminating Recommendation by Understanding the Explicit Item Relations

Recent years have witnessed the prevalence of recommender systems in various fields, which provide a personalized recommendation list for each user based on various kinds of information. For quite a long time, most researchers have been pursing recommendation performances with predefined metrics, e.g., accuracy. However, in real-world applications, users select items from a huge item list by considering their internal personalized demand and external constraints. Thus, we argue that explicitly modeling the complex relations among items under domain-specific applications is an indispensable part for enhancing the recommendations. Actually, in this area, researchers have done some work to understand the item relations gradually from “implicit” to “explicit” views when recommending. To this end, in this paper, we conduct a survey of these recent advances on recommender systems from the perspective of the explicit item relation understanding. We organize these relevant studies from three types of item relations, i.e., combination-effect relations, sequence-dependence relations, and external-constraint relations. Specifically, the combination-effect relation and the sequence-dependence relation based work models the intra-group intrinsic relations of items from the user demand perspective, and the external-constraint relation emphasizes the external requirements for items. After that, we also propose our opinions on the open issues along the line of understanding item relations and suggest some future research directions in recommendation area.     

融合元数据及隐式反馈信息的多层次联合学习推荐方法

基于隐式反馈信息的推荐是目前推荐系统领域的重要方法,能在一定程度上解决显式信息难以获得的问题。但由于隐式数据本身的特点单纯利用隐式反馈信息往往难以获取较好的推荐性能。针对此问题,本文提出一种融合元数据及隐式反馈信息的多层次深度联合学习（Multi-level Deep Joint Learning,简称MDJL）的推荐方法。它利用双深度神经网络共同学习,其中一个网络利用隐式反馈学习用户及项目个体个性化关系,另一个网络利用元数据学习高层次群体共性化关系,从而有效地表达用户偏好,使MDJL框架在个体及群体因素间达到平衡。实验结果表明,MDJL推荐算法在MovieLens 100K和MovieLens 1M两个公开数据集上均表现出更优越的推荐性能。     

基于显式与隐式反馈信息的概率矩阵分解推荐

针对现有的基于用户显式反馈信息的推荐系统推荐准确率不高的问题,提出了一种基于显式与隐式反馈信息的概率矩阵分解推荐方法。该方法综合考虑了显示反馈信息和隐式反馈信息,在对用户信任关系矩阵和商品评分矩阵进行概率分解的同时加入了用户评分记录的隐式反馈信息,优化训练模型参数,为用户提供精确的预测评分。实验结果表明,该方法可以有效地获得用户偏好,产生大量的准确度高的推荐。     

EARS: Emotion-aware recommender system based on hybrid information fusion

Recommender systems suggest items that users might like according to their explicit and implicit feedback information, such as ratings, reviews, and clicks. However, most recommender systems focus mainly on the relationships between items and the user’s final purchasing behavior while ignoring the user’s emotional changes, which play an essential role in consumption activity. To address the challenge of improving the quality of recommender services, this paper proposes an emotion-aware recommender system based on hybrid information fusion in which three representative types of information are fused to comprehensively analyze the user’s features: user rating data as explicit information, user social network data as implicit information and sentiment from user reviews as emotional information. The experimental results verify that the proposed approach provides a higher prediction rating and significantly increases the recommendation accuracy.     

融合知识图谱和评论文本的个性化推荐模型

推荐系统的目的是解决“信息过载”的问题,然而目前的研究方法大多利用用户和商品信息对用户兴趣进行建模,没有同时利用知识图谱构建用户模型来增强推荐系统的性能,因此提出了融合知识图谱和评论文本的个性化推荐模型。首先,通过不同类型的知识图谱分别关联用户项目和用户评论文本,扩展用户的兴趣和提取评论文本中的实体;其次,通过构造用户兴趣网络得到带有用户兴趣偏好的兴趣特征;然后,通过构造画像模块和情感模块的画像网络提取到带有用户情感倾向的画像特征;利用决策层进行点击率预测。最后在Amazon数据集上进行了实验比较,对所提模型的性能进行了评估,并与目前的融合知识图谱和评论文本的推荐模型进行比较,验证了所提模型的有效性。     

基于改进的倾向得分估计的无偏推荐模型

现实中推荐系统通常遭受着各种各样的偏置问题,例如曝光偏置、位置偏置和选择偏置。一个忽略偏置问题的推荐模型不能反映推荐系统的真实性能,且对于用户而言可能是不可信任的。先前的工作已经表明基于倾向得分估计的推荐模型能够有效缓解隐式反馈数据的曝光偏置,但是通常只考虑通过物品信息来估计倾向得分,这可能导致倾向得分估计不准确。为了提高倾向得分估计的准确性,提出配对倾向得分估计（MPE）方法。具体来说,该方法引入了用户流行度偏好的概念,通过计算用户流行度偏好和物品流行度的配对程度来对样本曝光率进行更加精确的建模,最后将提出的估计方法和一个主流的传统推荐模型以及一个无偏推荐模型进行集成并和包括前两者的三个基线模型进行对比。在公开数据集上的实验结果表明,结合MPE方法后的模型分别相比对应的基线模型在召回率、折损累计增益（DCG）和平均准确率（MAP）这三个评估指标上均有显著的提升;此外,通过实验结果还观察到性能的增益有很大一部分来自长尾物品,可见所提方法有助于提升推荐物品的多样性与覆盖率。     

A novel confidence estimation method for heterogeneous implicit feedback

Implicit feedback, which indirectly reflects opinion through user behaviors, has gained increasing attention in recommender system communities due to its accessibility and richness in real-world applications. A major way of exploiting implicit feedback is to treat the data as an indication of positive and negative preferences associated with vastly varying confidence levels. Such algorithms assume that the numerical value of implicit feedback, such as time of watching, indicates confidence, rather than degree of preference, and a larger value indicates a higher confidence, although this works only when just one type of implicit feedback is available. However, in real-world applications, there are usually various types of implicit feedback, which can be referred to as heterogeneous implicit feedback. Existing methods cannot efficiently infer confidence levels from heterogeneous implicit feedback. In this paper, we propose a novel confidence estimation approach to infer the confidence level of user preference based on heterogeneous implicit feedback. Then we apply the inferred confidence to both point-wise and pair-wise matrix factorization models, and propose a more generic strategy to select effective training samples for pair-wise methods. Experiments on real-world e-commerce datasets from Tmall.com show that our methods outperform the state-of-the-art approaches, considering several commonly used ranking-oriented evaluation criteria.     

Conversational Collaborative Recommendation – An Experimental Analysis

Traditionally, collaborative recommender systems have been based on a single-shot model of recommendation where a single set of recommendations is generated based on a user’s (past) stored preferences. However, content-based recommender system research has begun to look towards more conversational models of recommendation, where the user is actively engaged in directing search at recommendation time. Such interactions can range from high-level dialogues with the user, possibly in natural language, to more simple interactions where the user is, for example, asked to indicate a preference for one of k suggested items. Importantly, the feedback attained from these interactions can help to differentiate between the user’s long-term stored preferences, and her current (short-term) requirements, which may be quite different. We argue that such interactions can also be beneficial to collaborative recommendation and provide experimental evidence to support this claim.