Modeling Price-Aware Session-Based Recommendation Based on Graph Neural Network

Session-based Recommendation(SBR)aims to accurately recom-mend a list of items to users based on anonymous historical session sequences.Existing methods for SBR suffer from several limitations:SBR based on Graph Neural Network often has information loss when constructing session graphs;Inadequate consideration is given to influencing factors,such as item price,and users’dynamic interest evolution is not taken into account.A new session recommendation model called Price-aware Session-based Recommendation(PASBR)is proposed to address these limitations.PASBR constructs session graphs by information lossless approaches to fully encode the original session information,then introduces item price as a new factor and models users’price tolerance for various items to influence users’preferences.In addition,PASBR proposes a new method to encode user intent at the item category level and tries to capture the dynamic interest of users over time.Finally,PASBR fuses the multi-perspective features to generate the global representation of users and make a prediction.Specifically,the intent,the short-term and long-term interests,and the dynamic interests of a user are combined.Experiments on two real-world datasets show that PASBR can outperform representative baselines for SBR.

SGT:Session-based Recommendation with GRU and Transformer

Session-based recommendation aims to predict user preferences based on anonymous behavior sequences.Recent research on session-based recommendation systems has mainly focused on utilizing attention mechanisms on sequential patterns,which has achieved significant results.However,most existing studies only consider individual items in a session and do not extract information from continuous items,which can easily lead to the loss of information on item transition relationships.Therefore,this paper proposes a session-based recommendation algorithm(SGT)based on Gated Recurrent Unit(GRU)and Transformer,which captures user interests by learning continuous items in the current session and utilizes all item transitions on sessions in a more refined way.By combining short-term sessions and long-term behavior,user dynamic preferences are captured.Extensive experiments were conducted on three session-based recommendation datasets,and compared to the baseline methods,both the recall rate Recall@20 and the mean reciprocal rank MRR@20 of the SGT algorithm were improved,demonstrating the effectiveness of the SGT method.

Intention-aware for Session-based Recommendation with Multi-channel Network

Session-based recommendation predicts the user’s next action by exploring the item dependencies in an anonymous session.Most of the existing methods are based on the assumption that each session has a single intention,items irrelevant to the single intention will be regarded as noises.However,in real-life scenarios,sessions often contain multiple intentions.This paper designs a multi-channel Intention-aware Recurrent Unit(TARU)network to further mining these noises.The multi-channel TARU explicitly group items into the different channels by filtering items irrelevant to the current intention with the intention control unit.Furthermore,we propose to use the attention mechanism to adaptively generate an effective representation of the session’s final preference for the recommendation.The experimental results on two real-world datasets denote that our method performs well in session recommendation tasks and achieves improvement against several baselines on the general metrics.

BGNN: Behavior-aware graph neural network for heterogeneous session-based recommendation

Session-based recommendation(SBR)and multibehavior recommendation(MBR)are both important problems and have attracted the attention of many researchers and practitioners.Different from SBR that solely uses one single type of behavior sequences and MBR that neglects sequential dynamics,heterogeneous SBR(HSBR)that exploits different types of behavioral information(e.g.,examinations like clicks or browses,purchases,adds-to-carts and adds-to-favorites)in sequences is more consistent with real-world recommendation scenarios,but it is rarely studied.Early efforts towards HSBR focus on distinguishing different types of behaviors or exploiting homogeneous behavior transitions in a sequence with the same type of behaviors.However,all the existing solutions for HSBR do not exploit the rich heterogeneous behavior transitions in an explicit way and thus may fail to capture the semantic relations between different types of behaviors.However,all the existing solutions for HSBR do not model the rich heterogeneous behavior transitions in the form of graphs and thus may fail to capture the semantic relations between different types of behaviors.The limitation hinders the development of HSBR and results in unsatisfactory performance.As a response,we propose a novel behavior-aware graph neural network(BGNN)for HSBR.Our BGNN adopts a dual-channel learning strategy for differentiated modeling of two different types of behavior sequences in a session.Moreover,our BGNN integrates the information of both homogeneous behavior transitions and heterogeneous behavior transitions in a unified way.We then conduct extensive empirical studies on three real-world datasets,and find that our BGNN outperforms the best baseline by 21.87%,18.49%,and 37.16%on average correspondingly.A series of further experiments and visualization studies demonstrate the rationality and effectiveness of our BGNN.An exploratory study on extending our BGNN to handle more than two types of behaviors show that our BGNN can easily and effectively be extended to multibehavior scenarios.

KGSR-GG:A Noval Scheme for Dynamic Recommendation

Recommendation algorithms regard user-item interaction as a sequence to capture the user’s short-term preferences,but conventional algorithms cannot capture information of constantly-changing user interest in complex contexts.In these years,combining the knowledge graphwith sequential recommendation has gained momentum.The advantages of knowledge graph-based recommendation systems are that more semantic associations can improve the accuracy of recommendations,rich association facts can increase the diversity of recommendations,and complex relational paths can hence the interpretability of recommendations.But the information in the knowledge graph,such as entities and relations,often fails to be fully utilized and high-order connectivity is unattainable in graph modelling in knowledge graph-based sequential recommender systems.To address the above problems,a knowledge graph-based sequential recommendation algorithm that combines the gated recurrent unit and the graph neural network(KGSRGG)is proposed in the present work.Specifically,entity disambiguation in the knowledge graph is performed on the preprocessing layer;on the embedding layer,the TransR embedding technique is employed to process the user information,item information and the entities and relations in the knowledge graph;on the aggregation layer,the information is aggregated by graph convolutional neural networks and residual connections;and at last,on the sequence layer,a bi-directional gated recurrent unit(Bi-GRU)is utilized to model the user’s sequential preferences.The research results showed that this newalgorithm performed better than existing sequential recommendation algorithms on the MovieLens-1M and Book-Crossing datasets,as measured by five evaluation indicators.

A Novel IoT Application Recommendation System Using Metaheuristic Multi-Criteria Analysis

There are a variety of Internet of Things(IoT)applications that cover different aspects of daily life.Each of these applications has different criteria and sub-criteria,making it difficult for the user to choose.This requires an automated approach to select IoT applications by considering criteria.This paper presents a novel recommendation system for presenting applications on the IoT.First,using the analytic hierarchy process(AHP),a multi-layer architecture of the criteria and sub-criteria in IoT applications is presented.This architecture is used to evaluate and rank IoT applications.As a result,finding the weight of the criteria and subcriteria requires a metaheuristic approach.In this paper,a sequential quadratic programming algorithm is used to find the optimal weight of the criteria and sub-criteria automatically.To the best of our knowledge,this is the first study to use an analysis of metaheuristic criteria and sub-criteria to design an IoT application recommendation system.The evaluations and comparisons in the experimental results section show that the proposed method is a comprehensive and reliable model for the construction of an IoT applications recommendation system.

Self-supervised graph learning with target-adaptive masking for session-based recommendation

Session-based recommendation aims to predict the next item based on a user’s limited interactions within a short period.Existing approaches use mainly recurrent neural networks(RNNs)or graph neural networks(GNNs)to model the sequential patterns or the transition relationships between items.However,such models either ignore the over-smoothing issue of GNNs,or directly use cross-entropy loss with a softmax layer for model optimization,which easily results in the over-fitting problem.To tackle the above issues,we propose a self-supervised graph learning with target-adaptive masking(SGL-TM)method.Specifically,we first construct a global graph based on all involved sessions and subsequently capture the self-supervised signals from the global connections between items,which helps supervise the model in generating accurate representations of items in the ongoing session.After that,we calculate the main supervised loss by comparing the ground truth with the predicted scores of items adjusted by our designed target-adaptive masking module.Finally,we combine the main supervised component with the auxiliary self-supervision module to obtain the final loss for optimizing the model parameters.Extensive experimental results from two benchmark datasets,Gowalla and Diginetica,indicate that SGL-TM can outperform state-of-the-art baselines in terms of Recall@20 and MRR@20,especially in short sessions.

Multimodal Interactive Network for Sequential Recommendation

Building an effective sequential recommendation system is still a challenging task due to limited interactions among users and items.Recent work has shown the effectiveness of incorporating textual or visual information into sequential recommendation to alleviate the data sparse problem.The data sparse problem now is attracting a lot of attention in both industry and academic community.However,considering interactions among modalities on a sequential scenario is an interesting yet challenging task because of multimodal heterogeneity.In this paper,we introduce a novel recommendation approach of considering both textual and visual information,namely Multimodal Interactive Network(MIN).The advantage of MIN lies in designing a learning framework to leverage the interactions among modalities from both the item level and the sequence level for building an efficient system.Firstly,an item-wise interactive layer based on the encoder-decoder mechanism is utilized to model the item-level interactions among modalities to select the informative information.Secondly,a sequence interactive layer based on the attention strategy is designed to capture the sequence-level preference of each modality.MIN seamlessly incorporates interactions among modalities from both the item level and the sequence level for sequential recommendation.It is the first time that interactions in each modality have been explicitly discussed and utilized in sequential recommenders.Experimental results on four real-world datasets show that our approach can significantly outperform all the baselines in sequential recommendation task.

BA-GNN: Behavior-aware graph neural network for session-based recommendation

Session-based recommendation is a popular research topic that aims to predict users’next possible interactive item by exploiting anonymous sessions.The existing studies mainly focus on making predictions by considering users’single interactive behavior.Some recent efforts have been made to exploit multiple interactive behaviors,but they generally ignore the influences of different interactive behaviors and the noise in interactive sequences.To address these problems,we propose a behavior-aware graph neural network for session-based recommendation.First,different interactive sequences are modeled as directed graphs.Thus,the item representations are learned via graph neural networks.Then,a sparse self-attention module is designed to remove the noise in behavior sequences.Finally,the representations of different behavior sequences are aggregated with the gating mechanism to obtain the session representations.Experimental results on two public datasets show that our proposed method outperforms all competitive baselines.The source code is available at the website of GitHub.

Quantifying predictability of sequential recommendation via logical constraints

The sequential recommendation is a compelling technology for predicting users’next interaction via their historical behaviors.Prior studies have proposed various methods to optimize the recommendation accuracy on different datasets but have not yet explored the intrinsic predictability of sequential recommendation.To this end,we consider applying the popular predictability theory of human movement behavior to this recommendation context.Still,it would incur serious bias in the next moment measurement of the candidate set size,resulting in inaccurate predictability.Therefore,determining the size of the candidate set is the key to quantifying the predictability of sequential recommendations.Here,different from the traditional approach that utilizes topological constraints,we first propose a method to learn inter-item associations from historical behaviors to restrict the size via logical constraints.Then,we extend it by 10 excellent recommendation algorithms to learn deeper associations between user behavior.Our two methods show significant improvement over existing methods in scenarios that deal with few repeated behaviors and large sets of behaviors.Finally,a prediction rate between 64%and 80%has been obtained by testing on five classical datasets in three domains of the recommender system.This provides a guideline to optimize the recommendation algorithm for a given dataset.

基于情境感知和序列模式挖掘的气象学习资源推荐算法

随着互联网的快速发展,气象部门职工作为学习者可以获得的学习资源得到极大丰富。信息超载导致检索合适的在线学习资源时遇到了困难;学习者在不同学习环境和序列访问模式上也有不同的学习需求。但是,现有的推荐系统,如基于内容的推荐和协同过滤,没有结合学习者的情境和序列访问模式,推荐结果准确度不高。本文提出了一种结合情境感知、序列模式挖掘和协同过滤算法的混合推荐算法来为学习者推荐学习资源。混合推荐算法中,情境感知被用来整合学习者的情境信息,如知识水平和学习目标;序列模式挖掘被用来对网络日志进行挖掘,发现学习者的序列访问模式;协同过滤被用来根据学习者的情境数据和序列访问模式为目标学习者计算预测并生成建议。实验和应用效果表明,该混合推荐算法推荐的质量和准确性方面优于其他推荐算法。

基于知识增强对比学习的长尾用户序列推荐算法

序列推荐根据目标用户的历史交互序列,预测其可能感兴趣的下一个物品。现有的序列推荐方法虽然可以有效捕获用户的历史交互序列中的长期依赖关系,但是无法为交互序列较短且用户数量庞大的长尾用户提供精确推荐。为了解决此问题,提出了一种基于知识增强对比学习的长尾用户序列推荐算法。首先,基于知识图谱中的丰富实体关系信息,构建一个基于语义的物品相似度度量,分别提取原始序列中物品的协同关联物品。然后,基于不同学习序列提出2种序列增强算子,通过增强自监督信号解决长尾用户序列训练数据不足的问题。最后,通过对比自监督任务和推荐主任务的网络参数共享的联合训练,为长尾用户提供更精确的序列推荐结果。在实际数据集上的实验结果表明,所提算法可以有效提高针对长尾用户的序列推荐精度。

融合时间感知和多兴趣提取网络的序列推荐

针对序列推荐任务中的时间动态性和多重兴趣建模问题,提出一种时间感知的项目嵌入方法,用于学习项目之间的时间关联性。在此基础上,提出一种融合时间感知和多兴趣提取网络的序列推荐(time-aware multi-interest sequence recommendation,TMISA)方法。TMISA采用自注意力序列推荐模型作为局部特征学习模块,以捕捉用户行为序列中的动态偏好;通过多兴趣提取网络对用户的全局偏好进行建模;引入门控聚合模块将局部和全局特征表示动态融合,生成最终的用户偏好表示。实验证明,在5个真实推荐数据集上,TMISA模型表现出卓越性能,超越了多个先进的基线模型。

融合项目特征级信息的稀疏兴趣网络序列推荐

在以往提取多兴趣嵌入的序列推荐模型中仅能通过聚类的方法发现少量兴趣概念,忽视项目交互序列中特征级信息对最终推荐结果的影响。针对此问题,对传统的多兴趣序列推荐模型进行改进,提出一种融合项目特征级信息的稀疏兴趣网络序列推荐模型。实验结果表明,相比其它模型,该模型可以更好捕捉用户的多样化偏好并缓解冷启动问题。在给定数据集上,该模型比传统的序列推荐模型在命中率上平均提高了6.4%,归一化折损累计增益平均提高了8.7%。

价格引导双流自注意力序列推荐模型

针对传统序列推荐算法捕获交互序列中的长期依赖性能力较弱,以及由于数据稀疏性导致推荐结果缺乏个性化的问题,提出了一种价格引导双流自注意力序列推荐模型。通过融合项目价格信息分析用户价格偏好并辅助计算项目相似度,提高推荐结果的个性化程度;将两种信息输入到两个独立的自注意力机制,学习不同位置的重要性、提取其特征,并将输出进行拼接后输入到门控单元学习时间依赖性,提高模型的长期依赖性建模能力。在三个公开数据集上验证了模型的有效性,命中率和归一化折损累积增益最低提升1.11%,最高提升5.34%。

时间感知的双塔型自注意力序列推荐模型

用户的偏好具有聚合性和漂移性。现有推荐算法在序列建模框架中融合了交互时间相关性的建模,取得了很大的性能改善,但它们在建模时仅考虑了交互的时间间隔,使得它们在捕捉用户偏好的时间动态方面存在局限性。首先,提出了一种新的时间感知的位置嵌入方法,将时间信息与位置嵌入相结合,帮助模型学习时间层面的项目相关性。随后,在时间感知位置嵌入基础上,提出了时间感知的双塔自注意力序列推荐模型(TiDSA)。TiDSA包含项目级和特征级的自注意力模块,分别从项目和特征两个角度对用户偏好随时间变化的过程进行分析,实现了对时间、项目和特征的统一建模,并且在特征级自注意力模块,设计了多维度的自注意力权重计算方式,从特征维度、项目维度和项目与特征交叉维度充分学习特征之间的相关性。最后,TiDSA将项目级与特征级的信息相融合得到最终的用户偏好表示,并根据该表示为用户提供可靠的推荐结果。四个真实推荐数据集的实验结果表明,TiDSA的性能优于许多先进的基线模型。

基于反向延长增强的对抗生成网络推荐算法

针对现有序列推荐模型因数据稀疏性严重难以达到最优性能的问题,提出了一种基于反向延长增强的生成对抗网络推荐算法。该方法通过对交互序列进行延长增强来获取高质量的训练数据,以缓解数据稀疏性带来的模型训练不充分的问题。首先,使用伪先验项将项目序列进行反向延长,深化项目序列特征;其次,延长增强的对象由短序列更改为所有用户序列,充分挖掘长序列中富含的上下文信息,缓解了增广序列中伪先验项占比过大而带来的噪声问题;最后,使用共享项目嵌入的生成对抗网络,通过判别器与生成器联合训练以提高模型推荐性能。在三个公开数据集上的实验结果表明,所提模型的命中率(HR@N)和归一化折损累计增益(NDCG@N)相较于最优基线ELECRec平均提升30%,验证了反向延长增强对挖掘序列特征和缓解数据稀疏性的有效性。

基于对比学习的多兴趣感知序列推荐系统

序列推荐的近几年工作通过聚类历史交互物品或者利用图卷积神经网络获取交互的多层次关联信息来细化用户兴趣.然而,这些方法没有考虑具有相似行为模式的用户之间的相互影响以及交互序列中时间间隔不均匀对用户兴趣的影响.基于上述问题,提出一种基于对比学习的多兴趣感知序列推荐模型MIRec,一方面考虑了序列内部的物品依赖和位置依赖等局部偏好信息,另一方面通过图信息聚合机制获取相似用户之间的全局偏好信息;然后将融合局部偏好和全局偏好的用户表示输入胶囊网络中,学习用户交互序列中的多兴趣表示;最后通过对比学习使用户的历史交互序列靠近增强的交互序列,获得对时间间隔不敏感的用户多兴趣表示,为用户提供更准确的推荐.所提模型在2个真实数据集上进行了充分实验,实验结果验证了所提模型的有效性.

基于双通道轻量图卷积的序列推荐算法

传统基于图神经网络的序列推荐算法,在构图阶段忽略了其他用户序列中项目的转换关系,针对这一问题,提出了一种基于双通道轻量图卷积的序列推荐算法。首先,为目标用户找到其邻居用户序列,将目标用户序列和得到的邻居序列合并成一个有向序列图,充分利用了用户之间潜在的协作信息。然后,通过双通道轻量图卷积,分别对2种序列进行信息传播,每个通道通过指数分母的形式组合每一层的信息,融合2个通道得到的嵌入生成最终的项目嵌入。最后,对得到的项目嵌入通过后几项取平均的方式提取短期偏好,再通过引入挤压激励网络的多头自注意力机制提取长期偏好,整合长短期偏好得到用户的最终偏好。在2个公开数据集Beauty和MovieLens-20M上进行充分的实验并验证了算法的有效性。

GraphMLP-Mixer:基于图-多层感知机架构的高效多行为序列推荐方法

在多行为序列推荐领域,图神经网络(GNNs)虽被广泛应用,但存在局限性,如对序列间协同信号建模不足和处理长距离依赖性等问题.针对这些问题,提出了一种新的解决框架GraphMLP-Mixer.该框架首先构造全局物品图来增强模型对序列间协同信号的建模,然后将感知机-混合器架构与图神经网络结合,得到图-感知机混合器模型对用户兴趣进行充分挖掘.GraphMLP-Mixer具有2个显著优势:一是能够有效捕捉用户行为的全局依赖性,同时减轻信息过压缩问题;二是其时间与空间效率显著提高,其复杂度与用户交互行为的数量成线性关系,优于现有基于GNN多行为序列推荐模型.在3个真实的公开数据集上进行实验,大量的实验结果验证了GraphMLP-Mixer在处理多行为序列推荐问题时的有效性和高效性.