User-item Relationships Research Articles

Disentangled Dynamic Graph Attention Network for Out-of-distribution Sequential Recommendation

Sequential recommendation, leveraging user-item interaction histories to provide personalized and timely suggestions, has drawn significant research interest recently. With the power of exploiting spatio-temporal dynamics, dynamic graph neural networks (DyGNNs) show great potential in sequential recommendation by modeling the dynamic relationship between users and items. However, spatio-temporal distribution shifts naturally exist in out-of-distribution sequential recommendation, where both user-item relationships and temporal sequences demonstrate pattern shifts. The out-of-distribution scenarios may lead to the failure of existing DyGNNs in handling spatio-temporal distribution shifts in sequential recommendation, given that the patterns they exploit tend to be variant w.r.t labels under distribution shifts. In this paper, we propose D isentangled I ntervention-based D ynamic graph A ttention networks with I nvariance Promotion ( I-DIDA ) to handle spatio-temporal distribution shifts in sequential recommendation by discovering and utilizing invariant patterns, ie , structures and features whose predictive abilities are stable across distribution shifts. Specifically, we first propose a disentangled spatio-temporal attention network to capture the variant and invariant patterns. By utilizing the disentangled patterns, we design a spatio-temporal intervention mechanism to create multiple interventional distributions and an environment inference module to infer the latent spatio-temporal environments, and minimize the invariance loss to leverage the invariant patterns with stable predictive abilities under distribution shifts. Extensive experiments demonstrate the superiority of our method over state-of-the-art sequential recommendation baselines under distribution shifts.

A Study of Recommendation Methods Based on Graph Hybrid Neural Networks and Deep Crossing

In the face of complex user behavior patterns and massive data, improving the performance of recommender system models is an urgent challenge. Traditional methods often struggle to effectively handle feature interactions and complex user-item relationships. Combining the advantages of graph neural networks and the Deep Crossing network, this paper proposes a recommendation method based on hybrid neural networks with Deep Crossing (Deep Crossing with Graph Convolution and GRU, DCGCN-GRU). First, by constructing the graph structure of users and items, higher-order feature representations are extracted, and node features are updated using a multilayer graph convolution operation. Then, the higher-order features learned by the graph convolution network are spliced and weighted with the original features to form new feature inputs. Next, a Gated Recurrent Unit (GRU) is introduced to capture the inter-feature temporal dynamic relationships and sequence information. Finally, the Deep Crossing model is utilized to learn the interactions between the fused features at multiple levels and enhance the interactions between the features. Comparative experiments on three public datasets, MovieLens-ml-25m, Book-Crossings, and Amazon Reviews’23, show that the model achieves significant improvements in accuracy, mean square error (MSE), and mean absolute error (MAE).

Analysis of recommendation systems based on knowledge graphs

Due to the rapid development of internet technology, recommendation systems have played a crucial role in improving user experience and enhancing user retention. Knowledge graphs (KG), a technique capable of capturing complex semantic relationships and contextual information, are gradually included in recommendation systems to augment their accuracy and intelligence. This paper reviews the application of knowledge graphs in recommendation systems, analyzing their unique advantages in handling user-item relationships. This paper comprehensively analyzes embedding methods based on tensor decomposition and translation, which primarily designed for static knowledge graphs. This study thoroughly explains the advantages and disadvantages of these methods in practical application. Moreover, this paper discusses the challenges faced by dynamic knowledge graphs, such as temporal data processing, real-time updates, and inference, proposing potential solutions and future research areas. Integrating knowledge graphs with machine learning techniques enhances the ability of social media recommendation systems to understand user preferences and deliver highly personalized recommendations effectively. This study provides theoretical support and practical guidance for the implementing of knowledge graphs in recommendation systems, holding significant academic value and practical significance.

Multi-Behavior Graph Neural Networks for Recommender System.

Recommender systems have been demonstrated to be effective to meet user's personalized interests for many online services (e.g., E-commerce and online advertising platforms). Recent years have witnessed the emerging success of many deep-learning-based recommendation models for augmenting collaborative filtering (CF) architectures with various neural network architectures, such as multilayer perceptron and autoencoder. However, the majority of them model the user-item relationship with single type of interaction, while overlooking the diversity of user behaviors on interacting with items, which can be click, add-to-cart, tag-as-favorite, and purchase. Such various types of interaction behaviors have great potential in providing rich information for understanding the user preferences. In this article, we pay special attention on user-item relationships with the exploration of multityped user behaviors. Technically, we contribute a new multi-behavior graph neural network (MBRec), which specially accounts for diverse interaction patterns and the underlying cross-type behavior interdependencies. In the MBRec framework, we develop a graph-structured learning framework to perform expressive modeling of high-order connectivity in behavior-aware user-item interaction graph. After that, a mutual relationship encoder is proposed to adaptively uncover complex relational structures and make aggregations across layer-specific behavior representations. Through comprehensive evaluation on real-world datasets, the advantages of our MBRec method have been validated under different experimental settings. Further analysis verifies the positive effects of incorporating the multi-behavioral context into the recommendation paradigm. In addition, the conducted case studies offer insights into the interpretability of user multi-behavior representations. We release our model implementation at https://github.com/akaxlh/MBRec.

Continuous Training of Recommendation System for Airbnb Listings Using Graph Learning

Recommender systems are getting increasingly important nowadays as they can boost user engagement and benefit businesses. However, there remain some unsolved problems. This paper will address two key performance issues. First, the limited ability to identify and leverage intrinsic relationships between data points. Second, the inability to adapt to new data. The first issue is proposed to be addressed through a Graph Neural Network (GNN) to curate better recommendations. GNN will be trained with Airbnb’s review data to utilize its outstanding expressive power to represent complex user-listing interactions at scale, followed by generating embeddings to compute the relevant recommendations to the users. With the generated embeddings, the recommender system will compute a recommendation list to every user based on the embedding similarity between the user and listings or the user’s first-ever reviewed listing and listings. The second issue is proposed to be resolved by incorporating Continuous Training. The proposed recommender system employs GraphSAGE with a customized Rating-Weighted Triplet Ranking Loss function, which outperformed unsupervised GraphSAGE. Offline simulation validated the recommender system's ability to learn from the latest data and improve over time. Overall, the proposed user-to-item (U2I) recommendation rating-weighted GraphSAGE substantially increased by 99.88% in hit-rate@5 and 98.15% in coverage. This offers an effective solution for enhancing the recommender system for Airbnb listings. This research validates the efficacy of GNN-based recommendations in capturing user-item relationships to aid in predicting relevant recommendations, thus significantly driving up the adoption of GNN-based recommender systems.

Personalized Multimedia Recommendation Systems Using Higher-Order Tensor Singular-Value-Decomposition

Because of rapid growth of multimedia data over the Internet, the infobesity has been emerging in recent years. Many recommender systems (RSs) have been proposed using a variety of techniques, including artificial intelligence, machine learning, statistical analysis, and data mining. Nowadays, E-commerce companies such as Amazon, eBay, Netflix, etc. have applied RSs conveniently to provide better customer services than before by enabling customized multimedia-content recommendations. It is well known that classical RSs are almost all based on the user-item attribute matrices. However, this two-fold user-item relationship should be extended to the emerging many-fold relationship among an arbitrary number of attribute groups so that the corresponding new RSs may lead to better performances. Therefore, in this paper, we introduce a novel personalized multimedia recommender system (PMRS) according to our proposed new parallel higher-order tensor singular-value-decomposition (PHOTSVD) algorithm. This PHOTSVD algorithm is capable of accommodating an arbitrary number of entities such as social-media channels, users, queries, webpages, etc. in a robust RS. Furthermore, we also investigate the cold start and data bias problems critical to RSs. Finally, we compare the performances of our proposed new PMRS and three other existing tensor-based RSs over realworld data with respect to the well-adopted metric, namely normalized root-mean-square error (NRMSE). Our proposed new PMRS greatly outperforms the other three existing tensor-based RSs in terms of NRMSE.

Graph-Augmented Social Translation Model for Next-Item Recommendation

Next-item recommendation has been a hot research topic in academia and industry, which aims to help users discover the next interesting item. In this paper, we propose a novel solution, namely <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Graph-Augmented Social Translation model</i> (GAST), which investigates the utility of dynamic social influence for the task of next-item recommendation. Specifically, we introduce a gated graph convolution module to better model long-term user preference. Furthermore, we design a co-gating module to capture dynamic patterns at both sequential-level and social-level. In addition, a social-enhanced translation mechanism is devised to measure the intensity of user-item relationships. Extensive experiments under different recommendation scenarios demonstrate the rationality and effectiveness of our proposed GAST method over several state-of-the-art methods.

Self-supervised Multimodal Graph Convolutional Network for collaborative filtering

Collaborative filtering (CF) is a central solution for capturing various user-item relationships in building recommender systems. However, when the relationships are sparsely observed, it is challenging to obtain enough signals to infer precise user preferences. Recent studies have attempted to address the sparsity issue by incorporating multimodal information (e.g., image and text) into CF models. However, existing methods mainly focus on capturing modal-specific user preference with multiple unimodal graphs, ignoring the complex nature of user behavior, which is determined by an intricate fusion of multimodal information. Therefore, we develop a Self-supervised Multimodal Graph Convolutional Network (SMGCN), which aims to learn the cross-modal user preferences over multiple modalities with an expressive multimodal fusion on a single graph.More importantly, to facilitate and enhance multimodal fusion in SMGCN, we devise two novel self-supervised learning techniques. 1) Collaborative Multimodal Alignment (CMA) uses contrastive learning to align the domain-specific multimodal semantics with the user-item relational semantics. 2) Multimodal Consistency Regularization (MCR) alleviates the sensitivity on a certain modality and increases model robustness. The experimental results demonstrate that our model consistently outperforms advanced multimodal models on three benchmark datasets.

Discrete Listwise Content-aware Recommendation

To perform online inference efficiently, hashing techniques, devoted to encoding model parameters as binary codes, play a key role in reducing the computational cost of content-aware recommendation (CAR), particularly on devices with limited computation resource. However, current hashing methods for CAR fail to align their learning objectives (e.g., squared loss) with the ranking-based metrics (e.g., Normalized Discounted Cumulative Gain (NDCG)), resulting in suboptimal recommendation accuracy. In this article, we propose a novel ranking-based CAR hashing method based on Factorization Machine (FM), called Discrete Listwise FM (DLFM), for fast and accurate recommendation. Concretely, our DLFM is to optimize NDCG in the Hamming space for preserving the listwise user-item relationships. We devise an efficient algorithm to resolve the challenging DLFM problem, which can directly learn binary parameters in a relaxed continuous solution space, without additional quantization. Particularly, our theoretical analysis shows that the optimal solution to the relaxed continuous optimization problem is approximately the same as that of the original discrete optimization problem. Through extensive experiments on two real-world datasets, we show that DLFM consistently outperforms state-of-the-art hashing-based recommendation techniques.

Study of AI-Driven Fashion Recommender Systems

The rising diversity, volume, and pace of fashion manufacturing pose a considerable challenge in the fashion industry, making it difficult for customers to pick which product to purchase. In addition, fashion is an inherently subjective, cultural notion and an ensemble of clothing items that maintains a coherent style. In most of the domains in which Recommender Systems are developed (e.g., movies, e-commerce, etc.), the similarity evaluation is considered for recommendation. Instead, in the Fashion domain, compatibility is a critical factor. In addition, raw visual features belonging to product representations that contribute to most of the algorithm’s performances in the Fashion domain are distinguishable from the metadata of the products in other domains. This literature review summarizes various Artificial Intelligence (AI) techniques that have lately been used in recommender systems for the fashion industry. AI enables higher-quality recommendations than earlier approaches. This has ushered in a new age for recommender systems, allowing for deeper insights into user-item relationships and representations and the discovery patterns in demographical, textual, virtual, and contextual data. This work seeks to give a deeper understanding of the fashion recommender system domain by performing a comprehensive literature study of research on this topic in the past 10 years, focusing on image-based fashion recommender systems taking AI improvements into account. The nuanced conceptions of this domain and their relevance have been developed to justify fashion domain-specific characteristics.

A Hybrid Deep Learning Method to Extract Multi-features from Reviews and User–Item Relations for Rating Prediction

Currently, the Internet is widely used for shopping. Online reviews have become a crucial factor in helping people to make purchasing decisions. However, the large amount of data overwhelms most users, leading to the problem of information overload. To address this issue, researchers have proposed recommender systems as a solution. The most commonly used method is the collaborative filtering method, which analyzes users’ purchase history or behavior to make recommendations. In addition to user ratings, by analyzing users’ comments and the relationships between users and items more precise preferences can be obtained. In this study, the aspect-based rating prediction with a hybrid deep learning method (ARPH) is proposed. It consists of five parts: aspect detection, sentiment and semantic analysis, user preference analysis, graph attention network analysis, and rating prediction. It initially extracts the implicit aspect features and aspects’ sentiment–semantic features from user and item reviews. The convolutional neural network and matrix factorization methods are then used to generate the predicted ratings of items. Additionally, a graph attention network was built to calculate the predicted ratings based on the relationships between users and items. Finally, a multilayer perceptron was used to automatically adjust the weights for integrating these two predicted ratings. Our method utilizes user–item relationships to predict ratings when there are fewer user reviews. Conversely, the features derived from textual reviews were employed for rating prediction. The experimental results showed that extracting different features is useful in representing user and product preferences. The proposed method effectively improved the accuracy of the rating predictions.

Graph Transformer Collaborative Filtering Method for Multi-Behavior Recommendations

Graph convolutional networks are widely used in recommendation tasks owing to their ability to learn user and item embeddings using collaborative signals from high-order neighborhoods. Most of the graph convolutional recommendation tasks in existing studies have specialized in modeling a single type of user–item interaction preference. Meanwhile, graph-convolution-network-based recommendation models are prone to over-smoothing problems when stacking increased numbers of layers. Therefore, in this study we propose a multi-behavior recommendation method based on graph transformer collaborative filtering. This method utilizes an unsupervised subgraph generation model that divides users with similar preferences and their interaction items into subgraphs. Furthermore, it fuses multi-headed attention layers with temporal coding strategies based on the user–item interaction graphs in the subgraphs such that the learned embeddings can reflect multiple user–item relationships and the potential for dynamic interactions. Finally, multi-behavior recommendation is performed by uniting multi-layer embedding representations. The experimental results on two real-world datasets show that the proposed method performs better than previously developed systems.

DSER: Deep-Sequential Embedding for single domain Recommendation

Recently, Deep Neural Networks (DNNs) have proved their capability to model nonlinear relationships between users and items in recommender systems. Therefore, many researchers have exploited the DNN to model the non-linearity of individual interactions between users and items. However, it has been barely studied to model the non-linearity of a user’s sequential item interactions that may be the fundamental clue to represent a user’s interest naturally. This paper proposes a novel Deep Sequential Embedding for a single domain Recommendation based on implicit feedback, named DSER. It exploits Doc2vec techniques to convert sequential user–item interactions, rather than textual information, to the feature vectors of users and items. In our framework, a user’s interaction is like a document containing items as words in the word embedding techniques. The obtained user and item vectors are then fed to Multi-Layer Perceptron (MLP) to model a high level of non-linearity for user–item interactions. Finally, the non-linearity of MLP is fused with the linear user–item relationships trained by matrix factorization to predict the possibility that a target user likes items. Extensive experiments on four real-world datasets demonstrate significant improvements of our DSER over state-of-the-art approaches. Moreover, empirical evidence shows that using word embedding offers considerably better predictive performance on sparse data of the smart tourism field, whose new user ratio is relatively high.

Weighted Similarity and Core-User-Core-Item Based Recommendations.

In traditional recommendation algorithms, the users and/or the items with the same rating scores are equally treated. In real world, however, a user may prefer some items to other items and some users are more loyal to a certain item than other users. In this paper, therefore, we propose a weighted similarity measure by exploiting the difference in user-item relationships. In particular, we refer to the most important item of a user as his core item and the most important user of an item as its core user. We also propose a Core-User-Item Solver (CUIS) to calculate the core users and core items of the system, as well as the weighting coefficients for each user and each item. We prove that the CUIS algorithm converges to the optimal solution efficiently. Based on the weighted similarity measure and the obtained results by CUIS, we also propose three effective recommenders. Through experiments based on real-world data sets, we show that the proposed recommenders outperform corresponding traditional-similarity based recommenders, verify that the proposed weighted similarity can improve the accuracy of the similarity, and then improve the recommendation performance.

Efficient Algebraic Multigrid Methods for Multilevel Overlapping Coclustering of User-Item Relationships

Various digital data sets that encode user-item relationships contain a multilevel overlapping cluster structure. The user-item relation can be encoded in a weighted bipartite graph and uncovering these overlapping coclusters of users and items at multiple levels in the bipartite graph can play an important role in analyzing user-item data in many applications. For example, for effective online marketing, such as placing online ads or deploying smart online marketing strategies, identifying co-occurring clusters of users and items can lead to accurately targeted advertisements and better marketing outcomes. In this paper, we propose fast algorithms inspired by algebraic multigrid methods for finding multilevel overlapping cocluster structures of feature matrices that encode user-item relations. Starting from the weighted bipartite graph structure of the feature matrix, the algorithms use agglomeration procedures to recursively coarsen the bipartite graphs that represent the relations between the coclusters on increasingly coarser levels. New fast coarsening routines are described that circumvent the bottleneck of all-to-all similarity computations by exploiting measures of direct connection strength between row and column variables in the feature matrix. Providing accurate coclusters at multiple levels in a manner that can scale to large data sets is a challenging task. In this paper, we propose heuristic algorithms that approximately and recursively minimize normalized cuts to obtain coclusters in the aggregated bipartite graphs on multiple levels of resolution. Whereas the main novelty and focus of the paper lies in algorithmic aspects of reducing computational complexity to obtain scalable methods specifically for large rectangular user-item matrices, the algorithmic variants also define several new models for determining multilevel coclusters that we justify intuitively by relating them to principles that underlie collaborative filtering methods for user-item relationships. Experimental results show that the proposed algorithms successfully uncover the multilevel overlapping cluster structure for artificial and real data sets. Summary of Contribution: This paper develops new and efficient computational methods for finding the multilevel overlapping cocluster structure of feature matrices that encode user-item relationships. We base our approach on the use of pairwise similarity measures between features, seeking clusters of points that are similar to each other and dissimilar from the points outside the cluster. We approximately solve the problem of finding optimal overlapping coclusters on multiple levels by employing a framework that is based on efficient multilevel methods that have been used previously to solve sparse linear systems and to cluster graphs. Our main contribution is that we extend these methods in efficient manners to find coclusters in the bipartite graphs that encode common and important user-item relationships or social network relations. The novel methods that we propose are inherently scalable to large problem sizes and are naturally able to uncover overlapping coclusters at multiple levels, whereas existing methods generally only find coclusters at the fine level. We illustrate the algorithm and its performance on some standard test problems from the literature and on a proof-of-concept real-world data set that relates LinkedIn users to their skills and expertise.

Item-side ranking regularized distillation for recommender system

Recent recommender system (RS) have adopted large and sophisticated model architecture to better understand the complex user-item relationships, and accordingly, the size of the recommender is continuously increasing. To reduce the high inference costs of the large recommender, knowledge distillation (KD), which is a model compression technique from a large pre-trained model (teacher) to a small model (student), has been actively studied for RS. The state-of-the-art method is based on the ranking distillation approach, which makes the student preserve the ranking orders among items predicted by the teacher. In this work, we propose a new regularization method designed to maximize the effect of the ranking distillation in RS. We first point out an important limitation and a room for improvement of the state-of-the-art ranking distillation method based on our in-depth analysis.Then, we introduce the item-side ranking regularization, which can effectively prevent the student with limited capacity from being overfitted and enables the student to more accurately learn the teacher’s prediction results. We validate the superiority of the proposed method by extensive experiments on real-world datasets.

Learning attention embeddings based on memory networks for neural collaborative recommendation

Recently, deep learning has dominated the recommender system, as it is able to effectively capture nonlinear and nontrivial user–item relationships, and perform complex nonlinear transformations. However, there are still some issues with respects to the existing methods. Firstly, they always treat user–item interactions independently, and may fail to cover more complex and hidden information that is inherently implicit in the local neighborhood surrounding an interaction sample. Secondly, by quantifying the dependence degree of user–item sequences, it demonstrates that both short-term and long-term dependent behavioral patterns co-exist. Unfortunately, typical deep learning methods might be problematic when coping with very long-term sequential dependencies. To address these issues, we propose a novel unified neural collaborative recommendation algorithm that capitalizes on memory networks for learning attention embedding from implicit interaction (NCRAE). Particularly, the attention is capable of learning the relative importance of different users and items from user–item interaction sequences, which provides a better solution for concentrating on inputs and helps to better memorize long-term sequential dependencies. Extensive experiments on three real-world datasets show significant improvements of our proposed NCRAE algorithm over the competitive methods. Empirical evidence shows that using memory networks for learning attention embeddings of users’ implicit interaction yields better recommendation performance.

Data-Driven Diffusion Recommendation in Online Social Networks for the Internet of People

Recommendation systems are gaining popularity with the proliferation of the Internet of People (IoP). The popularity and use of online social networks facilitate integrating these social relationships with recommender systems under a single framework of IoP. This article proposes a new approach for item recommendation based on the diffusion method that combines user relationships in social networks with user–item relationships derived from the IoP. Especially, a resource redistribution process is explored in the user–object network that gives mass diffusion a higher recommendation accuracy and heat conduct a greater diversity by considering the social degree of users whilst calculating the user degree in the network. A tuning parameter is introduced to adjust the weight of resources that the objects finally receives from users based on their social relationships. Finally, extensive experiments conducted on the real-world datasets which contain friendship relationships, demonstrate the efficiencies of our proposed method in achieving notable performance improvements in terms of the recommendation accuracy, service diversity, and practical dependability.

Learning to Match on Graph for Fashion Compatibility Modeling

Understanding the mix-and-match relationships between items receives increasing attention in the fashion industry. Existing methods have primarily learned visual compatibility from dyadic co-occurrence or co-purchase information of items to model the item-item matching interaction. Despite effectiveness, rich extra-connectivities between compatible items, e.g., user-item interactions and item-item substitutable relationships, which characterize the structural properties of items, have been largely ignored. This paper presents a graph-based fashion matching framework named Deep Relational Embedding Propagation (DREP), aiming to inject the extra-connectivities between items into the pairwise compatibility modeling. Specifically, we first build a multi-relational item-item-user graph which encodes diverse item-item and user-item relationships. Then we compute structured representations of items by an attentive relational embedding propagation rule that performs messages propagation along edges of the relational graph. This leads to expressive modeling of higher-order connectivity between items and also better representation of fashion items. Finally, we predict pairwise compatibility based on a compatibility metric learning module. Extensive experiments show that DREP can significantly improve the performance of state-of-the-art methods.

RETRACTED ARTICLE: Improvising the performance of image-based recommendation system using convolution neural networks and deep learning

Recommendation systems now hold special significance, for in a world full of choices, order is the need of the hour. Without proper sorting, the gift of choice means nothing. The online retail world is fast-paced and ever-growing. With the exponential waning of attention span, it has become crucial to convert a casual visitor into a buyer within a limited window. Different ways can be used to do this: analysing buying patterns, surveys, user–user relationships, user-item relationships, and so on. This can be done with simple data analysis or with complex algorithms—the data must be harnessed one way or another. Deep learning is a branch of machine learning that has now become synonymous with computer vision, as these deep architectures closely emulate the biological process of vision. In this paper, the primary focus is the incorporation of a recommendation system with the visual features of products. This is done with the help of a deep architecture and a series of “convolution” operations that cause the overlapping of edges and blobs in images. We find that when the dimensionality problem has been dealt with, the features extracted serve as good quality representations of the images. Our empirical study compares the different linear and nonlinear reduction techniques on convolutional neural network features for building a recommendation model entirely based on the images.