User-item Interaction Data Research Articles

Knowledge-Aware Dual-Channel Graph Neural Networks For Denoising Recommendation

Abstract Knowledge graph (KG) is introduced as side information into recommender systems, which can alleviate the sparsity and cold start problems in collaborative filtering. Existing studies mainly focus on modeling users’ historical behavior data and KG-based propagation. However, they have the limitation of ignoring noise information during recommendation. We consider that noise exists in two parts (i.e. KG and user-item interaction data). In this paper, we propose Knowledge-aware Dual-Channel Graph Neural Networks (KDGNN) to improve the recommendation performance by reducing the noise in the recommendation process. Specifically, (1) for the noise in KG, we design a personalized gating mechanism, namely dual-channel balancing mechanism, to block the propagation of redundant information in KG. (2) For the noise in user-item interaction data, we integrate personalized and knowledge-aware signals to capture user preferences fully and use personalized knowledge-aware attention to denoise user-item interaction data. Compared with existing KG-based methods, we aim to propose a knowledge-aware recommendation method from a new perspective of denoising. We perform performance analysis on three real-world datasets, and experiment results demonstrate that KDGNN achieves strongly competitive performance compared with several compelling state-of-the-art baselines.

ALCR: Adaptive loss based critic ranking toward variational autoencoders with multinomial likelihood and condition for collaborative filtering

Research on variational autoencoders for collaborative filtering is gradually focusing on implicit feedback. However, most existing studies have two limitations: (1) they overlook the impact of user–item interaction data in implicit feedback on the representations of both users and items, which can affect the latent representations; (2) their attention is mainly focused on the immediate feedback of recommended items, ignoring interactions between feedback and ground-truth values, and neglecting the difference on loss functions between different training processes. To address these limitations, we first propose a condition for variational autoencoders to control user and item representations to learn more useful information from the latent representations. Then, we train an adaptive loss critic ranking to directly provide ranking scores in collaborative filtering recommendations, which aims to minimize loss and improve interactions during different critic training processes. Extensive experiments on three big real-world social media datasets demonstrate that this approach outperforms the existing twelve models under NDCG and Recall metric estimation settings and significantly improves the performance of a variety of prediction models.

Dual disentanglement of user–item interaction for recommendation with causal embedding

To achieve personalized recommendations, the recommender system selects the items that users may like by learning the collected user–item interaction data. However, the acquisition and use of data usually form a feedback loop, which leads to recommender systems suffering from popularity bias. To solve this problem, we propose a novel dual disentanglement of user–item interaction for recommendation with causal embedding (DDCE). Different from the existing work, our innovation is we take into account double-end popularity bias from the user-side and the item-side. Firstly, we perform a causal analysis of the reasons for user–item interaction and obtain the causal embedding representation of each part according to the analysis results. Secondly, on the item-side, we consider the influence of item attributes on popularity to improve the reliability of the item popularity. Then, on the user-side, we consider the effect of the time series when obtaining users’ interest. We model the contrastive learning task to disentangle users’ long–short-term interests, which avoids the bias of long–short-term interests overlapping, and use the attention mechanism to realize the dynamic integration of users’ long–short-term interests. Finally, we realize the disentanglement of user–item interaction reasons by decoupling user interest and item popularity. We experiment on two real-world datasets (Douban Movie and KuaiRec) to verify the significance of DDCE, the average improvement of DDCE in three evaluation metrics (NDCG, HR, and Recall) compared to the state-of-the-art model are 5.1106% and 4.1277% (MF as the backbone), 3.8256% and 3.2790% (LightGCN as the backbone), respectively.

IHG4MR: Interest-oriented heterogeneous graph for multirelational recommendation

Multirelational recommendation usually considers multiple types of user–item interaction data. Recently, graph convolutional networks (GCNs) have been widely used for recommendation systems. However, most existing GCN-based recommendation models only utilize one type of interactive data, ignoring other types of interactive data. At the same time, it is worth noting that GCN-based recommendation models are prone to oversmoothing problems. This means that when GCN-based recommendation models stack more layers, they also import noisy messages from users who have no common interest with the target user, resulting in a recommendation performance bottleneck. Consequently, it is necessary to reform the traditional GCN to make it suitable for a multirelational recommendation. A novel multirelational recommendation model through an interest-oriented heterogeneous graph (IHG4MR) is proposed in this paper. To effectively capture information from high-level nodes in a heterogeneous graph, IHG4MR first utilizes user characteristics and graph structure to split users who have similar preferences and then employs these segmented users and their interacting items to build multiple new interactive graphs instead of the previous whole graph to implement graph convolution operations. IHG4MR reduces the negative information carried during embedding propagation of the graph convolutional layers, thereby mitigating the effect of oversmoothing. Extensive experimental results on two real world datasets show that IHG4MR generally outperforms existing state-of-the-art models, demonstrating the effectiveness of our model.

Meta-relation assisted knowledge-aware coupled graph neural network for recommendation

Currently, the sparsity of user–item interaction data limits the performance of recommender systems. To alleviate the problems caused by data sparsity, researchers are devoted to designing more powerful graph neural network models to fuse the auxiliary information of users and items (social relationships, item dependencies, etc.). However, the lack of in-depth exploration of auxiliary information and the lack of optimization of the spatially distributed properties of the generated representations (known as embeddings) make it difficult to further improve the recommendation performance of these models. To address the above challenges, we propose a meta-relation-assisted knowledge-aware coupled graph neural network (MKCGN). Specifically, we design meta-relationship-guided graph neural networks for capturing collaborative signals from user and item domains and introduce coupled graph neural networks to inject local relationships into user/item representations. In addition, we design an auxiliary task that optimizes the distribution properties (alignment and uniformity) of the representation on the unit hypersphere to improve the quality of the representation. To evaluate the performance of MKCGN, we compare it with the state-of-the-art model on two real-world datasets with average performance improvements of 5.26% and 4.87%(using HR@N and NDCG@N as evaluation metrics), respectively. Our implemented model is available via https://github.com/Ganoder/MKCGN.

Graph-Augmentation-Free Self-Supervised Learning for Social Recommendation

Social recommendation systems can improve recommendation quality in cases of sparse user–item interaction data, which has attracted the industry’s attention. In reality, social recommendation systems mostly mine real user preferences from social networks. However, trust relationships in social networks are complex and it is difficult to extract valuable user preference information, which worsens recommendation performance. To address this problem, this paper proposes a social recommendation algorithm based on multi-graph contrastive learning. To ensure the reliability of user preferences, the algorithm builds multiple enhanced user relationship views of the user’s social network and encodes multi-view high-order relationship learning node representations using graph and hypergraph convolutional networks. Considering the effect of the long-tail phenomenon, graph-augmentation-free self-supervised learning is used as an auxiliary task to contrastively enhance node representations by adding uniform noise to each layer of encoder embeddings. Three open datasets were used to evaluate the algorithm, and it was compared to well-known recommendation systems. The experimental studies demonstrated the superiority of the algorithm.

Explainable Integration of Social Media Background in a Dynamic Neural Recommender

Recommender systems nowadays are commonly deployed in e-commerce platforms to help customers making purchase decisions. Dynamic recommender considers not only static user-item interaction data, but the temporal information at the time of recommendation. Previous researches have suggested to incorporate social media as the temporal information in dynamic neural recommenders after transforming them into embeddings. While such an approach can potentially improve recommendation performance, the effectiveness is difficult to explain. In this article, we propose an explainable method to integrate social media in a dynamic neural recommender. Our method applies association rule mining, which can generate human-understandable behavior patterns from social media and e-commerce platforms. With real-world social media and e-commerce data, we show that the integration can improve accuracy by up to 14% while using the same data. Moreover, we can explain the positive cases by examining relevant association rules.

Graph convolutional network combining node similarity association and layer attention for personalized recommendation

Although current graph convolutional network (GCN) has achieved competitive performance in personalized recommendation systems, most of existing GCN based recommendation methods mainly rely on user–item interaction data and the fixed association weights of the nodes at different layers, which greatly limit them to further effectively learn the final embedding representation of nodes when interaction data is scarce. This paper proposes a GCN based recommendation model combining node similarity association and layer attention mechanism (NSAGCN) for predicting user–item interactions in personalized recommendation. The proposed NSAGCN model integrates the similarity associations of the same type nodes into a heterogeneous network based on the bipartite graph of user–item interaction to enrich semantic information of the original sparse interaction graph and more effectively learn the node embedding features. In addition, a layer attention strategy is used to aggregate the embeddings from different graph convolutional layers with various association weights according to the proximity to the target nodes. Extensive experiments on three public benchmark datasets (ML-100K, ML-1M, and Book-Crossing) show that the proposed NSAGCN model outperforms state-of-the-art models by an average improvement of 8.58%, 6.91%, and 6.33% in Recall, Precision, and Normalized Discounted Cumulative Gain (NDCG), respectively.

On the Relationship between Explanation and Recommendation: Learning to Rank Explanations for Improved Performance

Explaining to users why some items are recommended is critical, as it can help users to make better decisions, increase their satisfaction, and gain their trust in recommender systems (RS). However, existing explainable RS usually consider explanation as a side output of the recommendation model, which has two problems: (1) It is difficult to evaluate the produced explanations, because they are usually model-dependent, and (2) as a result, how the explanations impact the recommendation performance is less investigated. In this article, explaining recommendations is formulated as a ranking task and learned from data, similarly to item ranking for recommendation. This makes it possible for standard evaluation of explanations via ranking metrics (e.g., Normalized Discounted Cumulative Gain). Furthermore, this article extends traditional item ranking to an item–explanation joint-ranking formalization to study if purposely selecting explanations could reach certain learning goals, e.g., improving recommendation performance. A great challenge, however, is that the sparsity issue in the user-item-explanation data would be inevitably severer than that in traditional user–item interaction data, since not every user–item pair can be associated with all explanations. To mitigate this issue, this article proposes to perform two sets of matrix factorization by considering the ternary relationship as two groups of binary relationships. Experiments on three large datasets verify the solution’s effectiveness on both explanation ranking and item recommendation.

BiInfGCN: Bilateral Information Augmentation of Graph Convolutional Networks for Recommendation

The current graph-neural-network-based recommendation algorithm fully considers the interaction between users and items. It achieves better recommendation results, but due to a large amount of data, the interaction between users and items still suffers from the problem of data sparsity. To address this problem, we propose a method to alleviate the data sparsity problem by retaining user–item interactions while fully exploiting the association relationships between items and using side-information enhancement. We constructed a “twin-tower” model by combining a user–item training model and an item–item training model inspired by the knowledge distillation technique; the two sides of the structure learn from each other during the model training process. Comparative experiments were carried out on three publicly available datasets, using the recall and the normalized discounted cumulative gain as evaluation metrics; the results outperform existing related base algorithms. We also carried out extensive parameter sensitivity and ablation experiments to analyze the influence of various factors on the model. The problem of user–item interaction data sparsity is effectively addressed.

Conditional Collaborative Filtering Process for Top-K Recommender System (Student Abstract)

Conditional neural process (CNP) has been extensively applied into data analyzing tasks due to its excellent ability to make accurate predictions for incomplete data points. However, in literature there are only few works that studied the CNPin recommendation systems. In this work, we propose CCFP, which is a collaborative filtering method that differs from other CF models by incorporating CNP into encoder-decoder architecture. By analyzing the complete user-item interaction data, our model fits a global representation that can better rep-resenting the features of users and items. CCFP can significantly improve the recommendation performance compared to baselines by predicting items for the target users with their incomplete observation data.

Micro-behaviour with Reinforcement Knowledge-aware Reasoning for Explainable Recommendation

Existing practical recommendation scenarios involve multiple micro-behaviour user–item interactions, such as clicks, page views, add-to-favourites, and purchases, which provide fine-grained and a better in-depth understanding of the user’s preference. Furthermore, some recommendation methods have incorporated item knowledge into the micro-behaviour of user–item interaction. Although some have proved effective, two insights are often neglected. First, they fail to combine micro-behaviour with the relation of the knowledge graph (KG), and the semantic relationship between micro-behaviour and relation is not captured. Second, they do not provide explicit reasoning for micro-behaviour from user–item interaction data. These insights motivated us to propose a novel model of Micro-behaviour with Reinforcement Knowledge-aware Reasoning for Explainable Recommendation (MBKR), which incorporates micro-behaviour and the KG into reinforcement learning for explainable recommendation. Specifically, the model learns the behaviour by user–item propagation and the relation from the KG and combines the two to calculate the behavioural strength to mine user’s interests. In addition, we designed a Shawo-relational path that combines recommendation and interpretability by providing rational paths; these paths capture the semantics of behaviours and relations. Finally, we extensively evaluated our method on several large-scale benchmark datasets, and the results indicate that the proposed method is more effective in providing recommendations than state-of-the-art methods.

Modeling Product’s Visual and Functional Characteristics for Recommender Systems

An effective recommender system can significantly help customers to find desired products and assist business owners to earn more income. Nevertheless, the decision-making process of users is highly complex, not only dependent on the personality and preference of a user, but also complicated by the characteristics of a specific product. For example, for products of different domains (e.g., clothing versus office products), the product aspects that affect a user’s decision are very different. As such, traditional collaborative filtering methods that model only user-item interaction data would deliver unsatisfactory recommendation results. In this work, we focus on fine-grained modeling of product characteristics to improve recommendation quality. Specifically, we first divide a product’s characteristics into visual and functional aspects—i.e., the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">visual appearance</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">functionality</i> of the product. One insight is that, the visual characteristic is very important for products of visually-aware domain (e.g., clothing), while the functional characteristic plays a more crucial role for visually non-aware domain (e.g., office products). We then contribute a novel probabilistic model, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Visual and Functional Probabilistic Matrix Factorization</i> (VFPMF), to unify the two factors to estimate user preferences on products. Nevertheless, such an expressive model poses efficiency challenge in parameter learning from implicit feedback. To address the technical challenge, we devise a computationally efficient learning algorithm based on alternating least squares. Furthermore, we provide an online updating procedure of the algorithm, shedding some light on how to adapt our method to real-world recommendation scenario where data continuously streams in. Extensive experiments on four real-word datasets demonstrate the effectiveness of our method with both offline and online protocols.

Predicting Dynamic User–Item Interaction with Meta-Path Guided Recursive RNN

Accurately predicting user–item interactions is critically important in many real applications, including recommender systems and user behavior analysis in social networks. One major drawback of existing studies is that they generally directly analyze the sparse user–item interaction data without considering their semantic correlations and the structural information hidden in the data. Another limitation is that existing approaches usually embed the users and items into the different embedding spaces in a static way, but ignore the dynamic characteristics of both users and items. In this paper, we propose to learn the dynamic embedding vector trajectories rather than the static embedding vectors for users and items simultaneously. A Metapath-guided Recursive RNN based Shift embedding method named MRRNN-S is proposed to learn the continuously evolving embeddings of users and items for more accurately predicting their future interactions. The proposed MRRNN-S is extended from our previous model RRNN-S which was proposed in the earlier work. Comparedwith RRNN-S, we add the word2vec module and the skip-gram-based meta-path module to better capture the rich auxiliary information from the user–item interaction data. Specifically, we first regard the interaction data of each user with items as sentence data to model their semantic and sequential information and construct the user–item interaction graph. Then we sample the instances of meta-paths to capture the heterogeneity and structural information from the user–item interaction graph. A recursive RNN is proposed to iteratively and mutually learn the dynamic user and item embeddings in the same latent space based on their historical interactions. Next, a shift embedding module is proposed to predict the future user embeddings. To predict which item a user will interact with, we output the item embedding instead of the pairwise interaction probability between users and items, which is much more efficient. Through extensive experiments on three real-world datasets, we demonstrate that MRRNN-S achieves superior performance by extensive comparison with state-of-the-art baseline models.

A two‐phase knowledge distillation model for graph convolutional network‐based recommendation

Graph convolutional network (GCN)-based recommendation has recently attracted significant attention in the recommender system community. Although current studies propose various GCNs to improve recommendation performance, existing methods suffer from two main limitations. First, user–item interaction data is generally sparse in practice, highlighting these methods' ineffectiveness in learning user and item feature representations. Second, they usually perform a dot-product operation to model and calculate user preferences on items, leading to inaccurate user preference learning. To address these limitations, this study adopts a design idea that sharply differs from existing works. Specifically, we introduce the knowledge distillation concept into GCN-based recommendation and propose a two-phase knowledge distillation model (TKDM) improving recommendation performance. In Phase I, a self-distillation method on a graph auto-encoder learns the user and item feature representations. This auto-encoder employs a simple two-layer GCN as an encoder and a fully connected layer as a decoder. On this basis, in Phase II, a mutual-distillation method on a fully connected layer is introduced to learn user preferences on items with triple-based Bayesian personalized ranking. Extensive experiments on three real-world data sets demonstrate that TKDM outperforms classic and state-of-the-art methods related to GCN-based recommendation problems.

A Survey on Accuracy-oriented Neural Recommendation: From Collaborative Filtering to Information-rich Recommendation

Influenced by the great success of deep learning in computer vision and language understanding, research in recommendation has shifted to inventing new recommender models based on neural networks. In recent years, we have witnessed significant progress in developing neural recommender models, which generalize and surpass traditional recommender models owing to the strong representation power of neural networks. In this survey paper, we conduct a systematic review on neural recommender models, aiming to summarize this field to facilitate researchers and practitioners working on recommender systems. Specifically, based on the data usage during recommendation modeling, we divide the work into collaborative filtering and information-rich recommendation: 1) collaborative filtering, which leverages the key source of user-item interaction data; 2) content enriched recommendation, which additionally utilizes the side information associated with users and items, like user profile and item knowledge graph; and 3) temporal/sequential recommendation, which accounts for the contextual information associated with an interaction, such as time, location, and the past interactions. After reviewing representative work for each type, we finally discuss some promising directions in this field.

Collaborative filtering grounded on knowledge graphs

Matrix Factorization (MF) is a widely used collaborative filtering technique for effectively modeling a user-item interaction in recommender system. Despite the successful application of MF and its variants, the method proves to be effective only in situations where there is an abundance of user-item interactions. However, user-item interaction data are usually sparse, limiting the effectiveness of the method. In addressing this problem, recent methods have proposed to use knowledge graphs (KGs) as additional information to complement the sparse user-item interaction data. This has proved challenging given the complexity of the KG structure. In this paper, we propose a collaborative filtering method that takes advantage of knowledge graphs. More specifically, the embedding of a user and item are both grounded on the item’s attributes in the knowledge graph, and are aggregated with generic user and item representations modeled by MF for implicit recommendation. Our model has demonstrated to outperform the recent state-of-the-art method KGCN [18] in very sparse settings, showing an effective integration of KGs in recommender systems.

Knowledge-Guided Disentangled Representation Learning for Recommender Systems

In recommender systems, it is essential to understand the underlying factors that affect user-item interaction. Recently, several studies have utilized disentangled representation learning to discover such hidden factors from user-item interaction data, which shows promising results. However, without any external guidance signal, the learned disentangled representations lack clear meanings, and are easy to suffer from the data sparsity issue. In light of these challenges, we study how to leverage knowledge graph (KG) to guide the disentangled representation learning in recommender systems. The purpose for incorporating KG is twofold, making the disentangled representations interpretable and resolving data sparsity issue. However, it is not straightforward to incorporate KG for improving disentangled representations, because KG has very different data characteristics compared with user-item interactions. We propose a novel K nowledge-guided D isentangled R epresentations approach ( KDR ) to utilizing KG to guide the disentangled representation learning in recommender systems. The basic idea, is to first learn more interpretable disentangled dimensions (explicit disentangled representations) based on structural KG, and then align implicit disentangled representations learned from user-item interaction with the explicit disentangled representations. We design a novel alignment strategy based on mutual information maximization. It enables the KG information to guide the implicit disentangled representation learning, and such learned disentangled representations will correspond to semantic information derived from KG. Finally, the fused disentangled representations are optimized to improve the recommendation performance. Extensive experiments on three real-world datasets demonstrate the effectiveness of the proposed model in terms of both performance and interpretability.

Self-Propagation Graph Neural Network for Recommendation

In recommendation tasks, we model user preferences by learning node representations (i.e., user and item embeddings) based on the observed user-item interaction data, which is a bipartite graph. <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</b> raph <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</b> eural <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</b> etworks ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GNN</b> s) are widely used to refine the representations by exploring the topology of the graph: embeddings of neighbors are propagated to each node to reconstruct its embeddings. However, the propagation strategy in existing GNNs is empirical and defective: (1) a substantial proportion of links are missed in the sparse observed graph, which causes ineffective and biased propagation; and (2) the propagation weights are determined by a coarse pre-defined rule, which only takes the degree of nodes into consideration. In this paper, we propose a dense and data-driven propagation mechanism for GNNs. Considering the graph we use to propagate embeddings in recommendation tasks is extremely sparse, we complement it and use the predicted graph as the new propagation tool. We learn the propagation matrix from the data, and propose a <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">S</b> elf-propagation <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</b> raph <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</b> eural <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</b> etwork ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">SGNN</b> ). Since it is very space- and time-consuming to maintain a large and dense propagation matrix, we factorize it for storing and updating. In this paper, we propose three methods to complete the sparse graph and construct the propagation matrix: (1) we complete the graph based on a recommendation model; (2) we measure the node distance based on spectral clustering; (3) we predict missing links of the graph based on predictive embeddings. In SGNN, the embeddings can be propagated to not only the observed neighbors, but also the potential yet unobserved neighbors, and the propagation weights are learned based on the connection strength. Comprehensive experiments on three real-world datasets demonstrate the effectiveness and efficiency of our proposed model: SGNN outperforms recent state-of-the-art GNNs significantly. Codes are available on <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Wenhui-Yu/LCFN</uri> .

Graph Convolutional Embeddings for Recommender Systems

Modern recommender systems (RS) work by processing a number of signals that can be inferred from large sets of user-item interaction data. The main signal to analyze stems from the raw matrix that represents interactions. However, we can increase the performance of RS by considering other kinds of signals like the context of interactions, which could be, for example, the time or date of the interaction, the user location, or sequential data corresponding to the historical interactions of the user with the system. These complex, context-based interaction signals are characterized by a rich relational structure that can be represented by a multi-partite graph. Graph Convolutional Networks (GCNs) have been used successfully in collaborative filtering with simple user-item interaction data. In this work, we generalize the use of GCNs for N-partite graphs by considering N multiple context dimensions and propose a simple way for their seamless integration in modern deep learning RS architectures. More specifically, we define a graph convolutional embedding layer for N-partite graphs that processes user-item-context interactions and constructs node embeddings by leveraging their relational structure. Experiments on several datasets show the benefits of the introduced GCN embedding layer by measuring the performance of different context-enriched tasks.