Fine-grained Preferences Research Articles

TriMLP : A Foundational MLP-Like Architecture for Sequential Recommendation

In this work, we present TriMLP as a foundational MLP-like architecture for the sequential recommendation, simultaneously achieving computational efficiency and promising performance. First, we empirically study the incompatibility between existing purely MLP-based models and sequential recommendation, that the inherent fully-connective structure endows historical user–item interactions (referred as tokens) with unrestricted communications and overlooks the essential chronological order in sequences. Then, we propose the MLP-based Triangular Mixer to establish ordered contact among tokens and excavate the primary sequential modeling capability under the standard auto-regressive training fashion. It contains (1) a global mixing layer that drops the lower-triangle neurons in MLP to block the anti-chronological connections from future tokens and (2) a local mixing layer that further disables specific upper-triangle neurons to split the sequence as multiple independent sessions. The mixer serially alternates these two layers to support fine-grained preferences modeling, where the global one focuses on the long-range dependency in the whole sequence, and the local one calls for the short-term patterns in sessions. Experimental results on 12 datasets of different scales from 4 benchmarks elucidate that TriMLP consistently attains favorable accuracy/efficiency tradeoff over all validated datasets, where the average performance boost against several state-of-the-art baselines achieves up to 14.88%, and the maximum reduction of inference time reaches 23.73%. The intriguing properties render TriMLP a strong contender to the well-established RNN-, CNN-, and Transformer-based sequential recommenders. Code is available at https://github.com/jiangyiheng1/TriMLP .

A novel fuzzy neural collaborative filtering for recommender systems

In collaborative filtering recommendations, part of studies mainly focus on quantitatively learning user preferences based on explicit rating information. However, due to the uncertainty and complexity of decision-making scenarios, user preferences usually express ambiguity and diversity. Therefore, to fully capture user preferences from both qualitative and quantitative perspectives and improve the accuracy and reliability of recommendations, we propose a novel fuzzy neural collaborative filtering for recommender systems. Firstly, we qualitatively divide user preferences into fine-grained categories based on picture fuzzy set and transform the rating matrix into four preference degree matrices. Then, we employ Bernoulli matrix factorization to independently learn preference features of each submatrix to obtain picture fuzzy numbers. To enhance the adaptability of picture fuzzy set in recommender systems, we design an improved scoring function based on picture fuzzy number to effectively distinguish differences in user preference levels. In addition, we use a simple deep neural framework to quantitatively extract global preferences of users and fuse it with fine-grained preferences of users to thoroughly predict user preferences. Experiments on four benchmark datasets show that the proposed model outperforms other comparison methods in terms of recommendation accuracy. Compared with the closest competitor method, our model has the highest improvements of 5.08% and 4.04% in the metrics HR@10 and NDCG@10, respectively.

A multi-view heterogeneous knowledge learning method for personalized POI recommendation

Existing POI recommendation methods often fail to capture the fine-grained preferences of users and face the challenge of modeling multiple relationships. Moreover, knowledge graph-based recommendation methods are limited in storing dynamic user trajectories, making them unsuitable for POI recommendation scenarios. In this paper, we propose a Multi-View Heterogeneous Knowledge learning model that utilizes techniques for heterogeneous knowledge representation learning and multi-view context modeling. Our model comprehensively models user preferences and the relationships between users and POIs by utilizing information from users’ visiting sequences and POI attributes knowledge graph. Specifically, we design a heterogeneous knowledge embedding method to learn the representation of users and POIs using POI attribute knowledge and users’ visiting sequences. Additionally, we constructed a user trajectory similarity graph and a POI attribute similarity graph to explore potential relations between users and between POIs. The former measures the similarity of user behaviors based on user visit sequences, and the latter quantifies the similarity between different POIs through a novel feature mapping method. Finally, we propose a multi-view hybrid learning method that combines unsupervised and supervised learning paradigms to model complex relationships, improving the overall recommendation performance. Extensive experiments on real-world datasets validate the effectiveness of our method.

Heterogeneous Adaptive Preference Learning for Recommendation

Graph-based collaborative filtering techniques have emerged as a promising recommendation approach by modeling user-item interaction as graphs. Recently, contrastive learning has been employed in graph collaborative through data augmentation, which can effectively offer data efficiency and reduce labeling costs. Nonetheless, most existing contrastive learning approaches overlook the heterogeneous auxiliary information pertaining to users and items, such as user social relationships and item categories, which are crucial to alleviate the data sparsity issue. In this paper, we propose a novel contrastive learning method, referred to as Heterogeneous Adaptive Preference Learning for Recommendation (HAPLRec), which explicitly incorporates fine-grained preference information from both users and items. Specifically, we construct user relationship graphs and item relationship graphs based on specific meta-paths in a heterogeneous graph. Subsequently, we conduct data augmentation on these graphs individually to obtain auxiliary contrastive tasks. Moreover, we introduce an optimization algorithm that leverages the gradient similarity between the main task and the auxiliary tasks, dynamically adjusting the weight assigned to each task to expedite achieving superior performance within a shorter time frame. The effectiveness of the proposed model is demonstrated through extensive experiments conducted on three publicly available datasets.

Dual-view multi-modal contrastive learning for graph-based recommender systems

Personalized recommender systems play a crucial role in various online content-sharing platforms (e.g., TikTok). The learning of representations for multi-modal content is pivotal in current graph-based recommender systems. Existing works aim to enhance recommendation accuracy by leveraging multi-modal features (e.g., image, sound, text) as side information for items. However, this approach falls short in fully discerning users' fine-grained preferences across different modalities. To tackle this limitation, this paper introduces the Dual-view Multi-Modal contrastive learning Recommendation model (DMM-Rec). DMM-Rec employs self-supervised learning to guide the learning of user and item representations within the multi-modal context. Specifically, to capture users' preferences for different modalities, we propose specific-modal contrastive learning. Simultaneously, to capture users' cross-modal preferences, cross-modal contrastive learning is introduced to uncover interdependencies in users' preferences across modalities. The contrastive learning tasks not only adaptively explore potential relations between modalities but also address the data sparsity challenge in recommender systems. Extensive experiments conducted on three datasets and compared against ten baselines demonstrate that DMM-Rec outperforms the strongest baseline by an average of 6.81%. These results underscore the effectiveness of considering multi-modal content in improving recommender systems.

Feature interactive graph neural network for KG-based recommendation

Graph neural network (GNN) is considered as the state-of-art method for KG-based recommendation. However, the existing GNN-based recommendation methods incorporating KG information fail to fully consider interactions between nodes in the process of message passing and aggregating, which will affect the performance improvement of recommendation. To resolve the above limitation, we propose a Feature Interactive Graph Neural Network for KG-based Recommendation (FIKGRec) to explicitly model sophisticated feature interactions from the complex structure of heterogeneous knowledge graph. The overall framework consists of three components: (1) For items, we construct item-KGs where the nodes (entities) denote items and items’ features, and edges represent the relations between entities. Modeling feature interaction can be thus transformed into modeling node (entity) interaction on the knowledge graph. Specifically, we integrate the collaborative signals into the process of KG signals propagation to capture more precise user preferences and then employ the feature entity interaction layer to incorporate the interaction information between entities in the process of neighbor aggregation of entities in item-KG. (2) For users, a preference-aware attention mechanism is designed to obtain the user’s fine-grained preference for items that have been interacted. (3) The final representations of users and items are fed to deep neural network (DNN) to model complex correlations between them. Extensive experiments on three real-world datasets demonstrate the better performance of our FIKGRec framework compared to state-of-the-arts methods.

SMAR: Summary-Aware Multi-Aspect Recommendation

Extracting user preferences and item features from reviews to assist recommendations is becoming increasingly popular. However, on the one hand, existing works generally select reviews based on how well user reviews match item reviews. They ignore that reviews may contain noise such as irrelevant phrases, which will affect the accuracy of selecting important reviews. In contrast, summaries written by users are abstracts of reviews that contain critical item feature information. They can be adopted to identify crucial reviews and further capture user’s fine-grained preferences from reviews. In addition, current methods do not consider that different items have different aspects in the same domain. They normally set a fixed number of aspects of the entire domain to get coarse-grained user preferences and item features. However, when modeling the user’s preferences for the current item, it might be more important to capture the corresponding aspects of the item preferences. Therefore, in this paper, we are motivated to propose a Summary-Aware Multi-Aspect Recommendation (SMAR). Specifically, we first construct a Summary-Aware Review Selection Module which adopts summaries to alleviate noise in reviews, identifying key reviews accurately. We then design a Summary-Aware Multi-Aspect Module which captures targeted user preferences towards the current item’s aspects. Finally, we employ Latent Factor Model to complete the recommendation process. The experimental results on Amazon datasets show that our method significantly outperfoms state-of-art approaches in terms of rating prediction accuracy.

Does the rule matter? A comparison of preference elicitation methods and voting rules based on data from an Austrian regional parliamentary election in 2019

Based on data collected in connection with the 2019 parliamentary election in the Austrian region of Styria, we analyze (the use of) different voting rules. Following previous empirical studies in the literature, we use the results of an empirical survey to show that the choice of a voting rule will impact the outcome of an election (if revealed preferences are sincere), at least in certain parts of the social ranking. In addition, we observe a certain desire for voting rules using more fine-grained preference information. In that context, we investigate the degree of consistency in the voters’ declaration of preferences, something of relevance when different voting rules, that require different levels of information, are used. Finally, we discuss the occurrence of strategic behavior that can be observed in the data.

KPRLN: deep knowledge preference-aware reinforcement learning network for recommendation

AbstractUser preference information plays an important role in knowledge graph-based recommender systems, which is reflected in users having different preferences for each entity–relation pair in the knowledge graph. Existing approaches have not modeled this fine-grained user preference feature well, as affecting the performance of recommender systems. In this paper, we propose a deep knowledge preference-aware reinforcement learning network (KPRLN) for the recommendation, which builds paths between user’s historical interaction items in the knowledge graph, learns the preference features of each user–entity–relation and generates the weighted knowledge graph with fine-grained preference features. First, we proposed a hierarchical propagation path construction method to address the problems of the pendant entity and long path exploration in the knowledge graph. The method expands outward to form clusters centered on items and uses them to represent the starting and target states in reinforcement learning. With the iteration of clusters, we can better learn the pendant entity preference and explore farther paths. Besides, we design an attention graph convolutional network, which focuses on more influential entity–relation pairs, to aggregate user and item higher order representations that contain fine-grained preference features. Finally, extensive experiments on two real-world datasets demonstrate that our method outperforms other state-of-the-art baselines.

Learning Aspect-Aware High-Order Representations from Ratings and Reviews for Recommendation

Textual reviews contain rich semantic information that is useful for making better recommendation, as such semantic information may indicate more fine-grained preferences of users. Recent efforts make considerable improvement on recommendation by integrating textual reviews in rating-based recommendations. However, there still exist major challenges on integrating textual reviews for recommendation. On the one hand, most existing works focus on learning a single representation from reviews but ignoring complex relations between users (or items) and reviews, which may fail to capture user preferences and item attributes together. On the other hand, these works independently learn latent representations from ratings and reviews while omitting correlations between rating-based features and review-based features, which may harm recommendation performance. In this article, we capture the aspect-aware relations by constructing heterogeneous graphs from reviews. Furthermore, we propose a new recommendation model, namely AHOR, to jointly distill rating-based features and review-based features, which are derived from ratings and reviews, respectively. To explore the multi-hop connectivity information between users, items, and aspects, a novel graph neural network is introduced to learn aspect-aware high-order representations. Experiments based on public datasets show that our approach outperforms state-of-the-art methods. We also provide detailed analysis on the high-order signals and the aspect importance to show the interpretability of our proposed model.

Dual Preference Distribution Learning for Item Recommendation

Recommender systems can automatically recommend users with items that they probably like. The goal of them is to model the user-item interaction by effectively representing the users and items. Existing methods have primarily learned the user’s preferences and item’s features with vectorized embeddings, and modeled the user’s general preferences to items by the interaction of them. In fact, users have their specific preferences to item attributes and different preferences are usually related. Therefore, exploring the fine-grained preferences as well as modeling the relationships among user’s different preferences could improve the recommendation performance. Toward this end, we propose a dual preference distribution learning framework (DUPLE) , which aims to jointly learn a general preference distribution and a specific preference distribution for a given user, where the former corresponds to the user’s general preference to items and the latter refers to the user’s specific preference to item attributes. Notably, the mean vector of each Gaussian distribution can capture the user’s preferences, and the covariance matrix can learn their relationship. Moreover, we can summarize a preferred attribute profile for each user, depicting his/her preferred item attributes. We then can provide the explanation for each recommended item by checking the overlap between its attributes and the user’s preferred attribute profile. Extensive quantitative and qualitative experiments on six public datasets demonstrate the effectiveness and explainability of the DUPLE method.

Pairwise Metric Learning With Angular Margin for Tag Recommendation

The users on the Internet have been growing exponentially, and tag recommendation can automatically provide users with a selection of tags of interest to meet their personalized needs. Users can utilize these tags to freely annotate their favorite resources, making them efficient and fast in retrieving related resources. Tensor factorization methods are commonly used in tag recommendation at present. These methods model the user × item × tag interactions, transform the latent feature representations of users, items and tags into low-rank matrices and use inner products for prediction. However, the problem of using inner product is that it does not satisfy the triangle inequality, it ignores the distance relationship among entity pairs and cannot capture the fine-grained preference information. Metric learning in recommendation domains focus on using pairwise loss, which assumes that different categories (such as users, items and tags) have fixed margins. Different categories often have different intra-class variations. With fixed margins, it is often difficult to accurately distinguish between positive and negative samples, thus reducing recommendation performance and limiting the expression ability of the model. In this study, the metric learning method is used to explore the distance relationship among user × item × tag triplet, and the existing metric learning based methods (namely LRML, CML, SML) are applied to the tag recommendation. A pairwise metric learning method with angular margin is proposed, named PMLT. The pairwise distance relationship between user-tag and item-tag is modeled for the information of different entities. And an extra angular margin regularizer is added to the original pairwise loss to control the size of angular margin for user-tag and item-tag respectively. The strength of the constrained angular margin regularizer is controlled to dynamically adjust the distance changes of entity. This method constrains the fixed margin and also the angular margin of user-tag and item-tag. Compared with the traditional metric learning method, this method can capture additional relationship structure and has good recommendation performance. Finally, we conducted extensive experiments on two datasets, LastFm and Movielens, and the experimental results showed that the proposed method PMLT outperform the state-of-the-art baseline in the evaluation metrics Recall@N and NDCG@N, and obtain better prediction quality. We also analyze the influence of different parameters and internal components on the performance of the proposed method, which improves the interpretability of the proposed method.

Cross-Task Knowledge Distillation in Multi-Task Recommendation

Multi-task learning (MTL) has been widely used in recommender systems, wherein predicting each type of user feedback on items (e.g, click, purchase) are treated as individual tasks and jointly trained with a unified model. Our key observation is that the prediction results of each task may contain task-specific knowledge about user’s fine-grained preference towards items. While such knowledge could be transferred to benefit other tasks, it is being overlooked under the current MTL paradigm. This paper, instead, proposes a Cross-Task Knowledge Distillation framework that attempts to leverage prediction results of one task as supervised signals to teach another task. However, integrating MTL and KD in a proper manner is non-trivial due to several challenges including task conflicts, inconsistent magnitude and requirement of synchronous optimization. As countermeasures, we 1) introduce auxiliary tasks with quadruplet loss functions to capture cross-task fine-grained ranking information and avoid task conflicts, 2) design a calibrated distillation approach to align and distill knowledge from auxiliary tasks, and 3) propose a novel error correction mechanism to enable and facilitate synchronous training of teacher and student models. Comprehensive experiments are conducted to verify the effectiveness of our framework in real-world datasets.

Adaptive Alleviation for Popularity Bias in Recommender Systems with Knowledge Graph

Recommender systems are known to suffer from the popularity bias problem: popular items are recommended frequently, and nonpopular ones rarely, if at all. Prior studies focused on tackling this issue by increasing the number of recommended nonpopular (long-tail) items. However, these methods ignore the users’ personal popularity preferences and increase the exposure rate of the nonpopular items indiscriminately, which may hurt the user experience because different users have diverse interests in popularity. In this work, we propose a novel debias framework with knowledge graph (AWING), which adaptively alleviates popularity bias from the users’ perspective. Concretely, we explore fine-grained preferences (including popularity preference) behind a user-item interaction by using the heterogeneous graph transformer over the knowledge graph embedded with popularity nodes and endow the preferences with explicit semantics. Based on this idea, we can manipulate how much popularity preference affects recommendation results and improves the exposure rate of nonpopular items while considering the popularity preferences of different users. Experiments on public datasets show that the proposed method AWING can effectively alleviate popularity bias and ensure the user experience at the same time. The case study further demonstrates the feasibility of AWING on the explainable recommendation task.

HSRec: Hierarchical self-attention incorporating knowledge graph for sequential recommendation

Modeling user’s fine-grained preferences and dynamic preference evolution from their chronological behaviors are challenging and crucial for sequential recommendation. In this paper, we develop a Hierarchical Self-Attention Incorporating Knowledge Graph for Sequential Recommendation (HSRec). HSRec models not only the user’s intrinsic preferences but also the user’s external potential interests to capture the user’s fine-grained preferences. Specifically, the intrinsic interest module and potential interest module are designed to capture these two preferences respectively. In the intrinsic interest module, user’s sequential patterns are characterized from their behaviors via the self-attention mechanism. As for the potential interest module, high-order paths can be generated with the help of the knowledge graph. Therefore, a hierarchical self-attention mechanism is designed to aggregate the semantic information of user interaction from these paths. Specifically, an entity-level self-attention mechanism is applied to capture the sequential patterns contained in the high-order paths while an interaction-level self-attention mechanism is designed to further capture the semantic information from user interactions. Moreover, according to the high-order semantic relevance, HSRec can explore the user’s dynamic preferences at each time, thus describing the user’s dynamic preference evolution. Finally, experiments conducted on three real world datasets demonstrate the state-of-the-art performance of the HSRec.

DualGCN: An Aspect-Aware Dual Graph Convolutional Network for review-based recommender

Recently, a variety of review-based recommendation systems that incorporate the valuable information extracted from user-generated textual reviews into user and item modeling have been proposed. However, the existing recommendations normally model reviews at the sentence level. They ignore the modeling of aspect words in reviews, which fails to capture user preferences and item attributes in a fine-grained way. In addition, few studies consider constructing user–item interaction based on review information extracted from the aspect level. In this paper, we are motivated to propose an Aspect-Aware Dual Graph Convolutional Network (DualGCN). Specifically, we first design an Aspect-GCN layer to model the message diffusion of an aspect graph constructed from reviews, capturing the overall description of an aspect in all reviews. We then propose a UI-GCN layer to model a user’s fine-grained preferences toward interacted items at the aspect level. Finally, we adopt a Factorization Machine model to accomplish the recommendation task. The experimental results demonstrate that our model significantly outperforms the related approaches w.r.t. the accuracy of both rating prediction and top-K ranking on Amazon and Yelp datasets.

GFE: General Knowledge Enhanced Framework for Explainable Sequential Recommendation

It is vital for sequential recommendation to provide accurate and explainable results for user, which can help them make better decisions. In this paper, we develop a General Knowledge Enhanced Framework for Explainable Sequential Recommendation (GFE) to capture user’s fine-grained preferences and dynamic preferences evolution. Specifically, the fine-grained preferences are modeled as intrinsic interests and external potential interests, which can be captured by sequential-aware interest and knowledge-aware interest modules respectively. Moreover, the high-order paths between each user-item pair are generated with the help of the knowledge graph, which contain abundant high-order semantic relevance among entities. To make better use of this character, we propose a hierarchical self-attention mechanism to aggregate the high-order semantic information from these knowledge paths, thus discovering user’s dynamic preferences evolution. According to these abilities, GFE can provide more reasonable explanations from the views of microcosm and macrocosm. Unlike other traditional explainable sequential recommendation models, GFE has the strong generalization to integrate with other pure sequential recommendation models and endow explainability to them. Based on this nature, we combine the GFE with two state-of-the-art sequential recommendation models and further propose two GFE-based models, called GFE-SASRec and GFE-TiSASRec, to show the availability of GFE. Finally, experiments conducted on three real-world public datasets demonstrate the state-of-the-art performance and the strong explainability of GFE.

FG-RS: Capture user fine-grained preferences through attribute information for Recommender Systems

Recommender system uses user-item historical interactions to portray user preferences. Due to the problem of data sparseness, auxiliary information is introduced to describe user preferences, such as user/item attribute information. However, some of these methods only consider user(item) attributes when modeling user preferences. Although another part of the methods interact with user attributes and item attributes, this interaction doesn’t consider the potential preference of a certain attribute of the user to a certain attribute of the item. This makes the model unable to capture fine-grained user preferences. In fact, capturing fine-grained user preferences in terms of attributes is very effective in improving the recommendation effect. Therefore, in this paper we propose a recommendation method to capture user fine-grained preferences through attribute information. Specifically, there are two elaborately designed modules, interactive preference module and attribute fine-grained preference module. The former uses user-item historical interactions to model user’s interaction preferences. In order to obtain the user’s fine-grained preferences, the latter interacts with each attribute of the user and all the attributes of the item and uses the attention mechanism to mine the user’s more fine-grained preferences on attributes. Extensive experiments on three publicly available datasets demonstrate the effectiveness of the proposed method.

Using latent features for building an interpretable recommendation system

PurposeAspects extracted from the user’s historical records are widely used to define user’s fine-grained preferences for building interpretable recommendation systems. As the aspects were extracted from the historical records, the aspects that represent user’s negative preferences cannot be identified because of their absence from the records. However, these latent aspects are also as important as those aspects representing user’s positive preferences for building a recommendation system. This paper aims to identify the user’s positive preferences and negative preferences for building an interpretable recommendation.Design/methodology/approachFirst, high-frequency tags are selected as aspects to describe user preferences in aspect-level. Second, user positive and negative preferences are calculated according to the positive and negative preference model, and the interaction between similar aspects is adopted to address the aspect sparsity problem. Finally, an experiment is designed to evaluate the effectiveness of the model. The code and the experiment data link is:https://github.com/shiyu108/Recommendation-systemFindingsExperimental results show the proposed approach outperformed the state-of-the-art methods in widely used public data sets. These latent aspects are also as important as those aspects representing the user’s positive preferences for building a recommendation system.Originality/valueThis paper provides a new approach that identifies and uses not only users’ positive preferences but also negative preferences, which can capture user preference precisely. Besides, the proposed model provides good interpretability.

Prior-based bayesian pairwise ranking for one-class collaborative filtering

In many real-world applications, only user-item interactions (one-class feedback) can be observed. The recommendation methods have been studied for personalized ranking with one-class feedback in recent years. Pairwise ranking methods have been widely used for dealing with the one-class problem with the assumption that users prefer their observed items over unobserved items. However, existing some items that users have not seen yet. It is unsuitable for treating all unobserved items of the user as negative feedback. In this paper, we propose a Prior-based Bayesian Pairwise Ranking (PBPR) model, which relaxes the simple pairwise preference assumption in previous works by further considering the pairwise preference between two unobserved items. Moreover, we calculate users' potential preference scores on unobserved items, i.e., prior information, based on historical interactions. The prior information can be used to measure the fine-grained preference difference between any two unobserved items of each user. Through extensive experiments on real-world datasets, we demonstrate the effectiveness of our proposed recommendation method.