由于老师让我整理今年的序列推荐论文,然后我就下载了这么多,包含KDD2020 SIGIR2020 WWW2020还有一些去年的但是没看的。一共是23篇,如下图所示:
这么多论文我准备花时间细看一下,然后写写总结之类的内容。
首先,我打算先把这些论文的摘要整理出来看看。
KDD2020Jointly Learning to Recommend and Advertise (字节跳动的)
摘要:
Online recommendation and advertising are two major income channels for online recommendation platforms (e.g. e-commerce and news feed site). However, most platforms optimize recommend-ing and advertising strategies by different teams separately via different techniques, which may lead to suboptimal overall performances. To this end, in this paper, we propose a novel two-level reinforcement learning framework to jointly optimize the recommending and advertising strategies, where the first level generates a list of recommendations to optimize user experience in the long run; then the second level inserts ads into the recommendation list that can balance the immediate advertising revenue from advertisers and the negative influence of ads on long-term user experience. To be specific, the first level tackles high combinatorial action space problem that selects a subset item from the large item space; while the second level determines three internally related tasks, i.e., (i) whether to insert an ad, and if yes, (ii) the optimal and (iii) the optimal location to insert. The experimental results based on real-world data demonstrate the effectiveness of the proposed framework. We have released the implementation code to ease reproductivity.
在线推荐和广告是在线推荐平台(如电子商务和新闻订阅网站)的两大收入来源。然而,大多数平台对不同团队的推荐和广告策略分别进行优化,采用不同的技术,可能导致整体表现不佳。为此,本文提出了一种新型的二级强化学习框架来联合优化建议修补和广告策略,其中一级生成推荐列表来优化用户体验;然后第二级在推荐列表中插入广告,以平衡来自广告商的即时广告收入和广告对长期用户体验的负面影响。具体地说,第一个层次解决了高组合操作空间问题,即从大的项目空间中选择子集项目;而第二层决定了三个内部相关的任务,即(i)是否插入广告,如果是,(ii)最优广告 (iii)插入的最优位置。基于实际数据的实验结果验证了该框架的有效性。
ClKM19Session-based Recommendation with Hierarchical Memory Networks
摘要:
The task of session-based recommendation aims to predict users’future interests based on anonymous historical sessions. Recent works have shown that memory models, which capture user preference from previous interaction sequence with long short-term or short-term memory, can lead to encouraging results in this problem. However, most existing memory models tend to regard each item as a memory unit, which neglects n-gram features and is insufficient to learn the user’s feature-level preferences. In this paper, we aim to leverage n-gram features and model users’ feature-level preferences in an explicit and effective manner. To this end, we present a memory model with multi-scale feature memory for session-based recommendation. A densely connected convolutional neural network (CNN) with short-cut path between upstream and downstream convolutional blocks is applied to build multi-scale features from item representations, and features in the same scale are combined with memory mechanism to capture users’ feature-level preferences. Furthermore, attention is used to adaptively select users’ multi-scale feature-level preferences for recommendation. Extensive experiments conducted on two benchmark datasets demonstrate the effectiveness of the proposed model in comparison with competitive baselines.
基于会话的推荐任务是基于匿名历史会话来预测用户的未来兴趣。最近的研究表明,记忆模型可以在这个问题上产生令人鼓舞的结果,它能捕捉到用户对先前交互序列的偏好,并具有长期或短期的记忆。然而,现有的大多数记忆模型往往把每一个记忆单元看作一个存储单元,忽略了gram特征,不足以学习用户的特征级偏好。在本文中,我们的目标是利用gram特性,以一种明确有效的方式对用户的特征级偏好进行建模。为此,我们提出了一个基于多尺度特征记忆推荐的记忆模型。应用一种上下游卷积块间具有短路径的密集连接卷积神经网络(CNN)从项目表示、同一尺度特征和记忆机制相结合建立多尺度特征,以捕捉用户的特征级偏好。此外,注意力被用来自适应地选择用户的多尺度特征级偏好进行推荐。在两个基准数据集上进行的实验表明,该模型与竞争基线相比是有效的。
WSDM18Sequential Recommendation with User Memory Networks
摘要
User preferences are usually dynamic in real-world recommender systems, and a user’s historical behavior records may not be equally important when predicting his/her future interests. Existing recommendation algorithms – including both shallow and deep approaches – usually embed a user’s historical records into a single latent vector/representation, which may have lost the per item- or feature-level correlations between a user’s historical records and future interests. In this paper, we aim to express, store, and manipulate users’ historical records in a more explicit, dynamic, and effective manner. To do so, we introduce the memory mechanism to recommender systems. Specifically, we design a memory-augmented neural network (MANN) integrated with the insights of collaborative filtering for recommendation. By leveraging the external memory matrix in MANN, we store and update users’ historical records explicitly, which enhances the expressiveness of the model. We further adapt our framework to both item- and feature-level versions and design the corresponding memory reading/writing operations according to the nature of personalized recommendation scenarios. Compared with state-of-the-art methods that consider users’ sequential behavior for recommendation, e.g., sequential recommenders with recurrent neural networks (RNN) or Markov chains, our method achieves significantly and consistently better performance on four real-world datasets.
在现实世界的推荐系统中,用户偏好通常是动态的,用户的历史行为记录在预测他/她的未来兴趣时可能并不重要。现有的推荐算法-包括浅层和深层访问-通常将用户的历史记录嵌入到一个单一的潜在向量/表示中,这可能会丢失用户历史记录和实际兴趣之间的每项或特征级关联。在本文中,我们的目标是以一种更明确、更动态、更有效的方式来表达、存储和操纵使用者的历史记录。为此,我们将记忆机制引入到推荐系统中。具体地说,我们设计了一个记忆增强神经网络(MANN)与协同过滤的思想相结合,用于推荐。通过利用MANN中的外部存储矩阵,我们显式地存储和更新用户的历史记录,从而增强了模特。我们进一步调整我们的框架以适应项目级和功能级版本,并根据个性化推荐场景的性质设计相应的内存读写操作。与考虑用户顺序推荐行为的最新方法(如使用递归神经网络(RNN)或Markovchains的顺序推荐方法)相比,我们的方法在四个真实数据集上取得了显著且一致的性能。
WWW2020Intention Modeling from Ordered and Unordered Facets for Sequential Recommendation
摘要:
Recently, sequential recommendation has attracted substantial attention from researchers due to its status as an essential service for e-commerce. Accurately understanding user intention is an important factor to improve the performance of recommendation system. However, user intention is highly time-dependent and flexible, so it is very challenging to learn the latent dynamic intention of users for sequential recommendation. To this end, in this paper, we propose a novel intention modeling from ordered and unordered facets (IMfOU) for sequential recommendation. Specifically, the global and local item embedding (GLIE) we proposed can comprehensively capture the sequential context information in the sequences and highlight the important features that users care about. We further design ordered preference drift learning(OPDL) and unordered purchase motivation learning (UPML) to obtain user’s the process of preference drift and purchase motivation respectively. With combining the users’ dynamic preference and current motivation, it considers not only sequential dependencies between items but also flexible dependencies and models the user purchase intention more accurately from ordered and un-ordered facets respectively. Evaluation results on three real-world datasets demonstrate that our proposed approach achieves better performance than the state-of-the-art sequential recommendation methods achieving improvement of AUC by an average of 2.26%.
近年来,顺序推荐作为电子商务的一项重要服务,受到了研究者们的广泛关注。准确理解用户意图是提高推荐系统性能的重要因素。然而,用户意图具有高度的时间依赖性和灵活性,因此在序列推荐中学习用户潜在的动态意图是非常困难的。为此,本文提出了一种新的基于有序和无序方面的意向建模方法(IMfOU)。具体地说,我们提出的全局和局部项嵌入(GLIE)可以全面地捕捉序列中的序列上下文信息,突出用户害怕的重要特征。进一步设计了有序偏好漂移学习(OPDL)和无序购买动机学习(UPML),分别对用户的偏好漂移过程和购买动机进行了分析。它结合了用户的动态偏好和当前动机,不仅考虑了商品之间的顺序依赖关系,而且还考虑了柔性依赖关系,分别从有序和非有序两个方面对用户的购买意愿进行了较为准确的建模。对三个真实数据集的评估结果表明,我们提出的方法比最先进的序贯推荐方法取得了更好的性能,平均AUC提高了2.26%。
WWW2020Future Data Helps Training- Modeling Future Contexts for Session-based Recommendation
摘要:
Session-based recommender systems have attracted much attention recently. To capture the sequential dependencies, existing methods resort either to data augmentation techniques or left-to-right style auto regressive training. Since these methods are aimed to model the sequential nature of user behaviors, they ignore the future data of a target interaction when constructing the prediction model for it. However, we argue that the future interactions after a target interaction, which are also available during training, provide a valuable signal on user preference and can be used to enhance the recommendation quality. Properly integrating future data into model training, however, is non-trivial to achieve, since it disobeys machine learning principles and can easily cause data leakage. To this end, we propose a new encoder-decoder framework namedGap-filling based Recommender(GRec), which trains the encoder and decoder by a gap-filling mechanism. Specifically, the encoder takes a partially-completed session sequence (where some items are masked by purpose) as input, and the decoder predicts these masked items conditioned on the en-coded representation. We instantiate the general GRec framework using convolutional neural network with sparse kernels, giving consideration to both accuracy and efficiency. We conduct experiments on two real-world datasets covering short-, medium-, and long-range user sessions, showing that GRec significantly outperforms the state-of-the-art sequential recommendation methods. More empirical studies verify the high utility of modeling future contexts under our GRec framework.
基于会话的推荐系统近年来受到了广泛的关注。为了捕捉序列依赖关系,现有的方法要么采用数据扩充技术,要么采用从左到右的自回归训练。由于这些方法的目的是对用户行为的连续性进行建模,因此在构建目标交互的预测模型时,它们忽略了目标交互的未来数据。然而,我们认为,在目标交互之后的未来交互,也可以在训练期间使用,提供用户偏好的有用信号,并可以用来加强推荐质量。然而,将未来的数据整合到模型训练中是非常重要的,因为它违反了机器学习原理,容易造成数据泄漏。为此,我们提出了一种新的编解码器框架,即基于间隙填充的推荐器(GRec),它通过一种间隙填充机制来训练编解码器。具体地说,编码器以部分完整的序列(其中一些项目被故意屏蔽)作为输入,解码器根据编码的表示来预测这些被屏蔽的项目。我们使用稀疏核卷积神经网络对通用的GRec框架进行了实例化,兼顾了精度和效率。我们在两个真实的数据集上进行了实验,包括短期、中期和长期用户会话,结果表明GRec明显优于最先进的顺序推荐方法。更多的实证研究证实了在我们的GRec框架下建模未来环境的高效用。
WWW2020A Contextualized Temporal Attention Mechanism for Sequential Recommendation
摘要
Predicting users’ preferences based on their sequential behaviors in history is challenging and crucial for modern recommender systems. Most existing sequential recommendation algorithms focus on transitional structure among the sequential actions, but largely ignore the temporal and context information, when modeling the influence of a historical event to current prediction.In this paper, we argue that the influence from the past events on a user’s current action should vary over the course of time and under different context. Thus, we propose a Contextualized Temporal Attention Mechanism that learns to weigh historical actions’influence on not only what action it is, but also when and how the action took place. More specifically, to dynamically calibrate the relative input dependence from the self-attention mechanism,we deploy multiple parameterized kernel functions to learn various temporal dynamics, and then use the context information to determine which of these reweighing kernels to follow for each input. In empirical evaluations on two large public recommendation datasets, our model consistently outperformed an extensive set of state-of-the-art sequential recommendation methods。
在现代推荐系统中,根据用户在历史上的顺序行为来预测用户的偏好是一项具有挑战性和关键性的工作。现有的序列推荐算法大多侧重于序列动作之间的过渡结构,但在建模历史事件对当前事件的影响时,大多忽略了时间和上下文信息预测。这篇论文,我们认为,过去事件对用户当前行为的影响应该随着时间的推移和在不同的环境下发生变化。因此,我们提出了一个情境化的临时注意机制,它不仅能衡量历史行为对行动是什么的影响,而且能衡量行动发生的时间和方式。更具体地说,为了从自我注意机制中动态校准相对输入依赖性,我们部署了多个参数化的核函数来学习不同的时间动态,然后利用上下文信息来确定每个输入要遵循哪些重加权核。在对两个大型公开推荐数据集的实证评估中,我们的模型始终优于一系列先进的顺序推荐方法
WWW2020Attentive Sequential Model of Latent Intent for Next ltem Recommendation
摘要
Users exhibit different intents across e-commerce services (e.g. dis-covering items, purchasing gifts, etc.) which drives them to interact with a wide variety of items in multiple ways (e.g. click, add-to-cart,add-to-favorites, purchase). To give better recommendations, it is important to capture user intent, in addition to considering their historic interactions. However, these intents are by definition latent, as we observe only a user’s interactions and not their underlying intent. To discover such latent intents, and use them effectively for recommendation, in this paper we propose anAttentiveSequentialmodel ofLatentIntent (ASLI in short). Our model first learns item similarities from users’ interaction histories via a self-attention layer, then uses a Temporal Convolutional Network layer to obtain a latent representation of the user’s intent from her actions on a particular category. We use this representation to guide an attentive model to predict the next item. Results from our experiments show that our model can capture the dynamics of user behavior and preferences, leading to state-of-the-art performance across datasets from two major e-commerce platforms, namely Etsy and Alibaba
用户在电子商务服务中表现出不同的意图(例如,不包括商品、购买礼品等),这促使他们以多种方式(如点击、添加到购物车、添加到收藏夹、购买)与各种商品进行交互。为了给出更好的建议,除了考虑用户的历史交互之外,捕捉用户的意图非常重要。然而,根据定义,这些意图是潜在的,因为我们只观察用户的交互,而不是他们的潜在意图。为了发现这些潜在意图,并将其有效地用于推荐,本文提出了一种潜在的潜在意向序列模型(简称ASLI)。我们的模型首先通过一个自注意力层从用户的交互历史中学习项目的相似性,然后使用时间卷积网络层从用户对特定类别的行为中获得潜在的意图表示。我们用这个表示来指导注意力模型来预测下一个项目。我们的实验结果表明,我们的模型能够捕捉用户行为和偏好的动态,从而在两大电子商务平台(Etsy和Alibaba)的数据集中获得最先进的性能
WWW2020Adaptive Hierarchical Translation-based Sequential Recommendation
摘要
We propose an adaptive hierarchical translation-based sequential recommendation called HierTrans that first extends traditional item-level relations to the category-level, to help capture dynamic sequence patterns that can generalize across users and time. Then unlike item-level based methods, we build a novel hierarchical team-poral graph that contains item multi-relations at the category-level and user dynamic sequences at the item-level. Based on the graph, Hier Trans adaptively aggregates the high-order multi-relations among items and dynamic user preferences to capture the dynamic joint influence for next-item recommendation. Specifically, the user translation vector in HierTrans can adaptively change based on both a user’s previous interacted items and the item relations in-side the user’s sequences, as well as the user’s personal dynamic preference. Experiments on public datasets demonstrate the proposed model HierTrans consistently outperforms state-of-the-art sequential recommendation methods
我们提出了一种自适应的基于层次翻译的顺序推荐,称为HierTrans,它首先将传统的项目级别关系扩展到类别级别,以帮助动态捕获跨用户和跨时间的序列模式。然后,与基于项目级的方法不同,我们构建了一个新的层次结构模型图,它在类别级别包含项目多关系,在项目级别包含用户动态序列。基于该图,对高阶多关系项和动态用户偏好进行了筛选,以获取下一项推荐的动态点影响。具体地说,HierTrans中的用户翻译向量可以根据用户先前的交互项和用户序列中的项关系以及用户的个人动态引用进行自适应更改。在公共数据集上的实验表明,所提出的模型HierTrans始终优于最先进的顺序推荐方法
SIGIR2020Next-item Recommendation with Sequential Hypergraphs
摘要
There is an increasing attention on next-item recommendation systems to infer the dynamic user preferences with sequential user interactions. While the semantics of an item can change over time and across users, the item correlations defined by user interactions in the short term can be distilled to capture such change, and help in uncovering the dynamic user preferences. Thus, we are motivated to develop a novel next-item recommendation framework empowered by sequential hypergraphs. Specifically, the framework:(i) adopts hypergraph to represent the short-term item correlations and applies multiple convolutional layers to capture multi-order connections in the hypergraph; (ii) models the connections between different time periods with a residual gating layer; and (iii)is equipped with a fusion layer to incorporate both the dynamic item embedding and short-term user intent to the representation of each interaction before feeding it into the self-attention layer for dynamic user modeling. Through experiments on datasets from the e-commerce sites Amazon and Etsy and the information sharing platform Goodreads, the proposed model can significantly outperform the state-of-the-art in predicting the next interesting item for each user.
下一项推荐系统越来越受到人们的关注,它通过连续的用户交互来推断用户的动态偏好。虽然一个项目的语义可以随着时间和用户的不同而变化,但是用户交互在短期内定义的项目相关性可以被提炼出来以捕捉这种变化,并有助于揭示动态的用户偏好。因此,我们被激励去开发一个新的下一项推荐框架,该框架由顺序超图授权。具体来说,该框架:(i)采用超图来表示短期项目相关性,并应用多个卷积层来捕获超图中的多阶连接;(ii)用剩余的选通层对不同时间段之间的连接进行建模;以及(iii)配备有融合层,将动态嵌入和短期用户意图结合到每个交互的表示中,然后将其输入自我注意层进行动态用户建模。通过对来自电子商务网站Amazon和Etsy以及信息共享平台Goodreads的数据集的实验,所提出的模型在预测每个用户的下一个感兴趣的项目时,能够显著地超过目前的水平。
SIGIR2020Group-Aware Long- and Short-Term Graph Representation Learning for Sequential Group Recommendation
摘要
Sequential recommendation and group recommendation are two important branches in the field of recommender system. While considerable efforts have been devoted to these two branches in an independent way, we combine them by proposing the novel sequential group recommendation problem which enables modeling group dynamic representations and is crucial for achieving better group recommendation performance. The major challenge of the problem is how to effectively learn dynamic group representations based on the sequential user-item interactions of group members in the past time frames. To address this, we devise a Group-aware Long- and short-term Graph Representation Learning approach, namely GLS-GRL, for sequential group recommendation. Specifically, for a target group, we construct a group-aware long-term graph to capture user-item interactions and item-item co-occurrence in the whole history, and a group-aware short-term graph to contain the same information regarding only the current time frame. Based on the graphs, GLS-GRL performs graph representation learning to obtain long-term and short-term user representations, and further adaptively fuse them to gain integrated user representations. Finally, group representations are obtained by a constrained user-interacted attention mechanism which encodes the correlations between group members. Comprehensive experiments demonstrate that GLS-GRLachieves better performance than several strong alternatives com-ing from sequential recommendation and group recommendation methods, validating the effectiveness of the core components inGLS-GRL
序列推荐和群推荐是推荐系统领域的两个重要分支。在对这两个分支进行了深入研究的基础上,我们提出了一个新的序列群推荐问题,该问题能够对群体动态表示进行建模,对获得更好的群体推荐性能至关重要。该问题的主要挑战是如何有效地学习基于过去时间框架内组成员的用户-项目交互的动态组表示。为了解决这一问题,我们设计了一种群体感知的长、短期图表示学习方法,即GLS-GRL,用于序列群推荐。具体地说,对于一个目标组,我们构造了一个组感知的长期图来捕捉整个历史中的用户-项目交互和项目-项目的共同发生,以及一个组感知的短期图来包含关于当前时间框架的相同信息。基于这些图,GLS-GRL进行图表示学习,以获得长期和短期用户表示,并进一步自适应地使用它们来获得完整的用户表示。最后,通过一个受约束的用户交互保持机制来获得组表示,该机制对组成员之间的关联进行编码。综合实验表明,GLS-GRL的性能优于序贯推荐法和群推荐法的几种强方案,验证了其核心组件GLS-GRL的有效性
SIGIR2020Time Matters- Sequential Recommendation with Complex Temporal Information
摘要
Incorporating temporal information into recommender systems has recently attracted increasing attention from both the industrial and academic research communities. Existing methods mostly reduce the temporal information of behaviors to behavior sequences for subsequently RNN-based modeling. In such a simple manner, crucial time-related signals have been largely neglected. This paper aims to systematically investigate the effects of the temporal information in sequential recommendations. In particular, we firstly discover two elementary temporal patterns of user behaviors: “absolute time patterns” and “relative time patterns”, where the former highlights user time-sensitive behaviors, e.g., people may frequently interact with specific products at certain time point, and the latter indicates how time interval influences the relationship between two actions. For seamlessly incorporating this information into a unified model, we devise a neural architecture that jointly learns those temporal patterns to model user dynamic preferences. Extensive experiments on real-world datasets demonstrate the superiority of our model,comparing with the state-of-the-arts.
将时态信息引入推荐系统,近年来引起了工业界和学术界的广泛关注。现有的建模方法大多是将行为的时间信息简化为基于RNN的行为序列。以这种简单的方式,关键时刻相关的信号在很大程度上被忽略了。本文旨在系统地研究时间信息在顺序推荐中的作用。特别是,我们首先发现了用户行为的两种基本的时间模式:“绝对时间模式”和“相对时间模式”,前者表现为对时间敏感的行为,比如人们可能在特定时间点频繁地与特定产品进行交互,后者则表明显示时间间隔影响二者之间的关系行动。为了将这些信息无缝地整合到一个统一的模型中,我们设计了一个神经体系结构,它联合学习那些临时模式来模拟用户的动态偏好。通过对真实世界数据集的大量实验,证明了该模型的优越性。
SIGIR2020Global Context Enhanced Graph Nerual Networks for Session-based Recommendation
摘要
Session-based recommendation (SBR) is a challenging task, which aims at recommending items based on anonymous behavior sequences. Almost all the existing solutions for SBR model user preference only based on the current session without exploiting the other sessions, which may contain both relevant and irrelevant item-transitions to the current session. This paper proposes a novel approach, calledGlobalContextEnhancedGraph NeuralNetworks(GCE-GNN) to exploit item transitions overall sessions in a more subtle manner for better inferring the user preference of the current session. Specifically, GCE-GNNlearns two levels of item embed-dings from session graph and global graph, respectively: (i)Sessiongraph, which is to learn the session-level item embedding by modeling pairwise item-transitions within the current session; and (ii)Global graph, which is to learn the global-level item embedding by modeling pairwise item-transitions overall sessions. In GCE-GNN,we propose a novel global-level item representation learning layer, which employs a session-aware attention mechanism to re-cursively incorporate the neighbors’ embeddings of each node on the global graph. We also design a session-level item representation learning layer, which employs a GNN on the session graph to learn session-level item embeddings within the current session. More-over,GCE-GNN aggregates the learnt item representations in the two levels with a soft attention mechanism. Experiments on three benchmark datasets demonstrate that GCE-GNN outperforms the state-of-the-art methods consistently.
基于会话的推荐(Session-based recommendation,简称SBR)是一项具有挑战性的任务,它基于匿名行为序列推荐项目。几乎所有现有的SBR模型用户偏好解决方案都只基于当前会话,而没有利用其他会话,其中可能包含到当前会话的相关和不相关的项转换。本文提出了一种新的方法,称为globalContextenhancedGraph NeuralNetworks(GCE-GNN),以更精细的方式利用所有会话中的项转换,从而更好地推断用户对当前会话的偏好。具体来说,GCE-gnn从Sessiongraph和globalgraph中获得两个层次的项目嵌入,分别是:(i)会话图,即通过在当前会话中修改成对的项目转换来学习会话级的项目嵌入;和(ii)全局图,通过对成对项目转换的建模来学习全局级的项目嵌入在所有的会议上。GCE-GNN提出了一种新的全局级项目表示学习层,它采用一种会话感知的注意机制,在全局图上重新粗略地合并每个节点的邻居嵌入。我们还设计了一个会话级项目表示学习层,它使用会话图上的GNN来学习当前会话中会话级项的嵌入。此外,GCE Gnn通过软注意机制在两个层次上对所学项目的表征进行了调整。在三个基准数据集上的实验表明,GCE-GNN始终优于现有的方法。
SIGIR2020Sequential Recommendation with Self- attentive Multi-adversarial Network
摘要
Recently, deep learning has made significant progress in the task of sequential recommendation. Existing neural sequential recommenders typically adopt a generative way trained with MaximumLikelihood Estimation (MLE). When context information (called factor) is involved, it is difficult to analyze when and how each individual factor would affect the final recommendation performance. For this purpose, we take a new perspective and introduce adversarial learning to sequential recommendation. In this paper, we present a Multi-Factor Generative Adversarial Network (MFGAN)for explicitly modeling the effect of context information on sequential recommendation. Specifically, our proposed MFGAN has two kinds of modules: a Transformer-based generator taking user behavior sequences as input to recommend the possible next items, and multiple factor-specific discriminators to evaluate the generated sub-sequence from the perspectives of different factors. To learn the parameters, we adopt the classic policy gradient method, and utilize the reward signal of discriminators for guiding the learning of the generator. Our framework is flexible to incorporate multiple kinds of factor information and is able to trace how each factor contributes to the recommendation decision over time. Extensive experiments conducted on three real-world datasets demonstrate the superiority of our proposed model over the state-of-the-art methods, in terms of effectiveness and interpretability.
近年来,深度学习在顺序推荐任务上取得了显著进展。现有的神经序贯推荐算法通常采用极大似然估计(MLE)训练的生成式方法。当涉及到上下文信息(称为因素)时,很难分析每个独立因素何时以及如何影响最终推荐表演。为了为此,我们以一个新的视角,将多元学习引入序贯推荐。本文提出了一个多因素生成对抗性网络(MFGAN),用于显式地模拟上下文信息对顺序推荐的影响。具体来说,我们提出的MFGAN有两种模块:一种是基于变压器的以用户行为序列为输入来推荐可能的下一个项目的生成器,以及从不同因素的角度评估生成的子序列的多因素专用鉴别器。对于学习者,我们采用经典的梯度学习策略。我们的框架能够灵活地整合多种因子信息,并且能够跟踪每个因子如何随着时间的推移对推荐决策做出贡献。在三个实际数据集上进行的扩展实验表明,我们提出的模型在有效性和可解释性方面优于现有的方法
SIGIR2020Sentiment-guided Sequential Recommendation
摘要
The existing sequential recommendation methods focus on model-ing the temporal relationships of user behaviors and are good at using additional item information to improve performance. However, these methods rarely consider the influences of users’ sequential subjective sentiments on their behaviors—and sometimes the temporal changes in human sentiment patterns plays a decisive role in users’ final preferences. To investigate the influence of temporal sentiments on user preferences, we propose generating preferences by guiding user behavior through sequential sentiments.Specifically, we design a dual-channel fusion mechanism. The main channel consists of sentiment-guided attention to match and guide sequential user behavior, and the secondary channel consists of sparse sentiment attention to assist in preference generation. In the experiments, we demonstrate the effectiveness of these two sentiment modeling mechanisms through ablation studies. Our approachoutperforms current state-of-the-art sequential recommendation methods that incorporate sentiment factors.
现有的序列推荐方法侧重于对用户行为的时间关系进行建模,能够很好地对附加的项目信息进行状态化以提高性能。然而,这些方法很少考虑用户连续的主观情绪对其行为的影响,有时人类情感模式的时间变化对用户的最终偏好起决定性作用。为了研究临时情绪对用户偏好的影响,我们提出通过顺序引导用户行为来生成偏好感情。特别是设计了一种双通道融合机制。主通道由情感引导的注意匹配和引导顺序用户行为组成,次通道由解析情感注意组成,辅助偏好生成。在实验中,我们通过消融研究证明了这两种感知模型机制的有效性。我们的方法比目前最先进的包含情感因素的序列推荐方法表现更好。
SIGIR2019A Collaborative Session-based Recommendation Approach with Parallel Memory Modules
摘要
Session-based recommendation is the task of predicting the next item to recommend when the only available information consists of anonymous behavior sequences. Previous methods for session-based recommendation focus mostly on the current session, ignoring collaborative information in so-called neighborhood sessions, sessions that have been generated previously by other users and reflect similar user intents as the current session. We hypothesize that the collaborative information contained in such neighborhood sessions may help to improve recommendation performance for the current session. We propose a Collaborative Session-based RecommendationMachine (CSRM), a novel hybrid framework to apply collaborative neighborhood information to session-based recommendations.CSRMconsists of two parallel modules: an Inner Memory En-coder (IME) and an Outer Memory Encoder (OME). TheIMEmodelsa user’s own information in the current session with the help of current Neural Networks (RNNs) and an attention mechanism.The OME exploits collaborative information to better predict the intent of current sessions by investigating neighborhood sessions.Then, a fusion gating mechanism is used to selectively combine information from theIMEandOMEso as to obtain the final representation of the current session. Finally, CSRM obtains a recommendation score for each candidate item by computing a bilinear match with the final representation. Experimental results on three public datasets demonstrate the effectiveness of CSRM compared to state-of-the-art session-based recommender systems. Our analysis ofCSRM’s recommendation process shows when and how collaborative neighborhood information and the fusion gating mechanism positively impact the performance of session-based recommendations
基于会话的推荐是指当唯一可用的信息是由匿名行为序列组成时,预测下一次推荐的任务。以往的基于会话的推荐方法主要集中在当前会话上,忽略所谓邻居会话中的协作信息,忽略其他用户先前生成的会话中的协作信息,并反映与当前会话相似的用户意图。我们假设这些邻里会话中包含的协作信息可能有助于提高当前推荐性能会议。我们提出了一种基于协作会话的推荐机(CSRM),它是一种将协作邻域信息应用于基于会话的推荐机制的混合框架建议.CSRM组成两个并行模块:一个内部存储器编码器(IME)和一个外部存储器编码器(OME)。用当前的神经网络帮助用户掌握当前的信息机制。OME通过调查邻里关系来更好地预测当前会话的内容会话。然后呢, 采用融合选通机制,有选择地组合来自所述会话的信息,以获得当前会话的最终表示。最后,CSRM获得通过计算与最终结果的双线性匹配来获得每个候选项的推荐分数表现力。实验性在三个公共数据集上的结果表明,与最先进的基于会话的通信系统相比,该方法是有效的。我们对SRM推荐过程的分析表明,协作邻域信息和融合选通机制何时以及如何对基于会话的推荐产生积极影响
SIGIR2020An Intent-guided Collaborative Machine for Session-based Recommendation
摘要
Session-based recommendation produces item predictions mainly based on anonymous sessions. Previous studies have leveraged collaborative information from neighbor sessions to boost the recommendation accuracy for a given ongoing session. Previous work of-ten selects the most recent sessions as candidate neighbors, thereby failing to identify the most related neighbors to obtain an effective neighbor representation. In addition, few existing methods simultaneously consider the sequential signal and the most recent interest in an ongoing session. In this paper, we introduce an intent-guided collaborative Machine for Session-based Recommendation(ICM-SR).ICM-SR encodes an ongoing session by leveraging the prior sequential items and the last item to generate an accurate session representation, which is then used to produce initial item predictions as intent. After that, we design an intent-guided neighbor detector to locate the correct neighbor sessions. Finally, the representations of the current session and the neighbor sessions are adaptively combined by a gated fusion layer to produce the final item recommendations. Experiments conducted on two public benchmark datasets show that ICM-SR achieves a significant improvement in terms of Recall and MRR over the state-of-the-art baselines
基于会话的推荐主要基于匿名会话生成项目预测。以前的研究已经利用了来自相邻会话的协同信息来提高给定会话的推荐精度。前面的工作选择最近的会话作为候选邻居,因此无法识别最相关的邻居以获得有效的邻居表示。此外,现有的方法很少同时考虑序列信号和当前会话中的最新兴趣。本文介绍了一种基于会话的内容导向协同推荐机(ICM-SR),它利用前一个序列项和最后一个项对正在进行的会话进行编码,生成一个准确的会话表示,并将其作为内容进行初始项预测。然后,我们设计了一个意图引导的邻居检测器来定位正确的邻居会话。最后,由选通融合层自适应地组合当前会话和相邻会话的表示,生成最终的项目推荐。在两个公共基准数据集上进行的实验表明,ICM-SR在召回率和MRR方面比现有基线有了显著的提高
RECSYS19Predictability Limits in Session-based Next ltem Recommendation
摘要
Session-based recommendations are based on the user’s recent actions,for example,the items they have viewed during the current browsing session or the sightseeing places they have just visited.Closely related is sequence-aware recommendation,where the choice of the next item should follow from the sequence of previous actions.We study seven benchmarks for session-based recommendation,covering retail,music and news domains to investigate how accurately user behavior can be predicted from the session histories. We measure the entropy rate of the data and estimate the limit of predictability to be between 44% and 73% in the included datasets.We establish some algorithm-specifc limits on prediction accuracy for Markov chains,association rules and k-nearest neighbors methods. With most of the analyzed methods,the algorithm design limits their performance with sparse training data.The session based k-nearest neighbors are least restricted in comparison and have room for improvement across all of the analyzed datasets
基于会话的推荐基于用户最近的操作,例如,他们在当前浏览会话中浏览过的项目或他们刚刚访问的观光场所。密切相关的是序列感知的推荐,在此情况下,应跟随序列之前的行为选择下一个项目。我们将研究七个基于会话的推荐基准,包括零售,音乐和新闻领域,以研究如何根据会话历史预测用户行为的准确性。我们测量数据的熵率,并估计所包含数据集中的可预测性范围在44%到73%之间。我们为Markov链,关联规则和k最近邻方法建立了算法特定的预测精度极限。对于大多数分析方法,算法设计都使用稀疏的训练数据来限制其性能。基于会话的k最近邻居在比较中受到的限制最少,并且在所有分析的数据集中都有改进的空间
CIKM19Rethinking the ltem Order in Session-based Recommendation with Graph Neural Networks
摘要
Predicting a user’s preference in a short anonymous interaction session instead of long-term history is a challenging problem in the real-life session-based recommendation, e.g., e-commerce and media stream. Recent research of the session-based recommender system mainly focuses on sequential patterns by utilizing the attention mechanism, which is straightforward for the session’s natural sequence sorted by time. However, the user’s preference is muchmore complicated than a solely consecutive time pattern in the transition of item choices. In this paper, therefore, we study theitem transition pattern by constructing a session graph and propose a novel model that collaboratively considers the sequence order and the latent order in the session graph for a session-based recommender system. We formulate the next item recommendation within the session as a graph classification problem. Specifically, we propose a weighted attention graph layer and a Readout function to learn embeddings of items and sessions for the next item recommendation. Extensive experiments have been conducted on two benchmark E-commerce datasets, Yoochoose and Diginetica, and the experimental results show that our model outperforms other state-of-the-art methods.
在基于会话的推荐(如电子商务和媒体流)中,预测用户在短时间匿名交互过程中的偏好而不是长期历史是一个具有挑战性的问题。目前对基于会话的推荐系统的研究主要集中在使用注意机制的顺序模式上,这对于按时间排序的会话自然顺序是很直接的。然而,在项目选择的转换过程中,用户的偏好要比单纯的连续时间模式复杂得多。因此,本文通过构造会话图来研究会话图的过渡模式,并提出了一个新的模型,该模型综合考虑了会话图中的序列顺序和潜在顺序。我们将会话中的下一个项目推荐作为一个图分类问题。具体来说,我们提出了一个加权注意图层和一个读出函数来学习项目和会话的嵌入情况,以便下一个项目的建议。在这两个基准电子商务数据集上进行了大量的实验,实验结果表明我们的模型优于其他最先进的方法。
SIGIR2020Rethinking ltem Importance in Session-based Recommendation
摘要
Session-based recommendation aims to predict a user’s actions at the next timestamp based on anonymous sessions. Previous work mainly focuses on the transition relationship between items that the user interacted with during an ongoing session. They generally fail to pay enough attention to the importance of the items involved in these interactions in terms of their relevance to user’s main intent. In this paper, we propose a Session-based Recommendationapproach with an Importance Extraction Module, i.e., SR-IEM, that considers both a user’s long-term and recent behavior in an ongoing session. We employ a modified self-attention mechanism to estimate item importance in a session, which is then used to predict user's long-term preference. Item recommendations are produced by combining the user’s long-term preference and their current interest as conveyed by the last item they interacted with. Comprehensive experiments are conducted on two publicly available benchmark datasets. The proposed SR-IEM model outperforms start-of-the-art baselines in terms of Recall and MRR for the task of session-based recommendation. In addition, compared to state-of-the-art models, SR-IEM has a reduced computational complexity
基于会话的推荐是基于匿名会话来预测用户在下一个时间戳上的行为。以前的工作主要集中在用户正在进行的会话中与之交互的项之间的转换关系。他们通常都会注意到这些交互中涉及的项目的重要性,因为它们与用户的主帐篷相关。在本文中,我们提出了一种基于会话的推荐方法,该方法带有一个重要性提取模块,即SR-IEM,它考虑了用户在一个会话中的长期和近期行为。我们采用一种改进的自我注意机制来估计会话中的项目重要性,并以此来预测用户的长期偏好。商品推荐是通过将用户的长期偏好和他们与之交互的最后一个商品所传达的当前兴趣相结合而产生的。在两个公开的基准数据集上进行了综合实验。在基于会话的推荐任务中,所提出的SR-IEM模型在召回率和MRR方面优于artbaselines。此外,与最新的模型相比,SR-IEM具有更低的计算复杂度
SIGIR2020Sequential-based Adversarial Optimisation for Personalised Top-N ltem Recommendation
摘要
Personalised top-N item recommendation systems aim to generate a ranked list of interesting items to users based on their interactions (e.g. click, purchase and rating). Recently, various sequential-based factorized approaches have been proposed to exploit deep neural networks to effectively capture the users’ dynamic preferences from their sequences of interactions. These factorized approaches usually rely on a pairwise ranking objective such as the bayesian Personalised Ranking (BPR) for optimization. However, previous works have shown that optimising factorised approaches with BPR can hinder the generalization, which can degrade the quality of item recommendations. To address this challenge, we propose a Sequential-based Adversarial Optimisation (SAO) framework that effectively enhances the generalisation of sequential-based factorised approaches. Comprehensive experiments on six public datasets demonstrate the effectiveness of the SAO framework in enhancing the performance of the state-of-the-art sequential-based factorised approach in terms of NDCG by 3-14%
个性化的top-N商品推荐系统旨在根据用户的互动(如点击、购买和评级)为用户生成一份有兴趣的商品列表。近年来,人们提出了各种基于序列的因子分解方法来利用深度神经网络从用户交互序列中有效地捕捉用户的动态偏好。这些因子化的ap方法通常依赖于成对的排名目标,例如贝叶斯个性化排名(BPR)来进行优化。然而,以往的研究表明,基于BPR的优化因子分解方法会阻碍泛化,从而降低项目推荐的质量。为了应对这一挑战,我们提出了一个基于序列的对抗性优化(SAO)框架,该框架有效地增强了基于序列的因子化方法的泛化。在六个公共数据集上的综合实验表明,SAO框架可以有效地将最先进的基于序列的因子化方法的NDCG提高3-14%
CIKM2019Session-based Recommendation with Hierarchical Memory Networks
摘要
The task of session-based recommendation aims to predict users’future interests based on anonymous historical sessions. Recent works have shown that memory models, which capture user preference from previous interaction sequence with long short-term or short-term memory, can lead to encouraging results in this problem. However, most existing memory models tend to regard each item as a memory unit, which neglects n-gram features and is insufficient to learn the user’s feature-level preferences. In this paper, we aim to leverage-gram features and model users’ feature-level preferences in an explicit and effective manner. To this end,we present a memory model with multi-scale feature memory for session-based recommendation. A densely connected convolutional neural network (CNN) with short-cut path between upstream and downstream convolutional blocks is applied to build multi-scale features from item representations, and features in the same scale are combined with memory mechanism to capture users’ feature-level preferences. Furthermore, attention is used to adaptively select users’ multi-scale feature-level preferences for recommendation. Extensive experiments conducted on two benchmark datasets demonstrate the effectiveness of the proposed model in comparison with competitive baselines
基于会话的推荐任务是基于匿名历史会话来预测用户的未来兴趣。从长期记忆模型中可以看出,在短期记忆模型中,短期记忆模型能够有效地解决这一问题。然而,现有的大多数记忆模型往往把每一个记忆单元看作一个存储单元,忽略了n-gram特征,不足以学习用户的特征级偏好。在本文中,我们的目标是利用gram特性,以一种明确有效的方式对用户的特征级偏好进行建模。为此,我们提出了一个基于多尺度特征记忆推荐的记忆模型。应用一种上下游卷积块间具有短路径的密集连接卷积神经网络(CNN)从项目表示、同一尺度特征和记忆机制相结合建立多尺度特征,以捕捉用户的特征级偏好。此外,注意力被用来自适应地选择用户的多尺度特征级偏好进行推荐。在两个基准数据集上进行的实验表明,该模型与竞争基线相比是有效的
SIGIR2020Session-based Recommendation with Hierarchical Leaping Networks
摘要
Session-based recommendation aims to predict the next item that users will interact based solely on anonymous sessions. In real-life scenarios, the user’s preferences are usually various, and distinguishing different preferences in the session is important. However previous studies focus mostly on the transition modeling between items, ignoring the mining of various user preferences. In this paper, we propose a Hierarchical Leaping Network (HLN) to explicitly model the users’ multiple preferences by grouping items that share some relationships. We first design a Leap Recurrent Unit (LRU)which is capable of skipping preference-unrelated items and accepting knowledge of previously learned preferences. Then we introduce a Preference Manager (PM) to manage those learned preferences and produce an aggregated preference representation each time LRU reruns. The final output of PM which contains multiple preferences of the user is used to make recommendations. Experiments on two benchmark datasets demonstrate the effectiveness of HLN. Furthermore, the visualization of explicitly learned subsequences also confirms our idea
基于会话的推荐旨在预测下一个用户将只基于匿名会话进行交互的项目。在现实生活中,用户的偏好通常是多种多样的,在会话中区分不同的偏好是很重要的。然而以往的研究主要集中在项目间的转换建模上,忽略了对用户偏好的挖掘。本文提出了一个层次跃迁网络(HLN),通过对共享关系的项目进行分组,对用户的多个偏好进行显式建模。我们首先设计了一个跳跃式重复单元(LRU),它能够跳过偏好无关的项目,并接受先前所学偏好的知识。然后引入一个偏好管理器(PM)来管理这些学习到的偏好,并在每次LRU重新运行时生成一个聚合的偏好表示。PM的最终输出包含用户的多个偏好,用于推荐。实验在两个基准数据集上验证了HLN的有效性。此外,显式学习的子序列的可视化也证实了我们的想法