User-item Bipartite Graph Research Articles

Explicitly Exploiting Implicit User and Item Relations in Graph Convolutional Network (GCN) for Recommendation

Most existing collaborative filtering-based recommender systems rely solely on available user–item interactions for user and item representation learning. Their performance often suffers significantly when interactions are sparse, as limited user and item interactions are insufficient for learning robust representations. To address this issue, recent research has explored additional information between users and items by leveraging the user–item bipartite graph. However, these methods have not fully exploited high-order neighborhood information, primarily using sampled interactions to enrich training data rather than integrating this information directly into representation learning. In this paper, we propose a novel model, EIR-GCN (Embedding Integration with Relational Graph Convolutional Network), which directly incorporates various types of collaborative relations, such as user–user and item–item interactions, into the embedding function for user preference modeling. Specifically, our model employs advanced graph convolutional network (GCN) techniques to integrate user–item, user–user, and item–item relations for comprehensive representation learning. EIR-GCN initially selects the most influential second-order neighbors from the user–item bipartite graph to form user–user and item–item connections. With these enriched connections, a message-passing method is adopted to learn node representations by aggregating messages from directly linked nodes, including first-order item neighbors and selected second-order user neighbors. Extensive experiments on several public datasets demonstrate that EIR-GCN outperforms strong baselines, including recent GCN-based models and those exploiting high-order information. Our results show that EIR-GCN achieves state-of-the-art performance and effectively addresses the sparsity issue, highlighting its robustness and efficacy in recommendation tasks.

A graph attention network with contrastive learning for temporal review-based recommendations

In recent years, review-based recommendations have recently attracted extensive attention from researchers. However, applying reviews to improve recommendation performance still faces some problems that remain unsolved: (1) Most existing works cannot capture the time-varying user preferences and high-order collaborative features. (2) Most of the existing works often use supervised learning to train models with a limited interaction between users and items, which is not sufficient to learn the more accurate recommendation models. To overcome these problems, we propose a new Graph Attention Network with Contrastive Learning for temporary review-based recommendation, named GANCL. Specifically, to capture dynamic user preferences and high-order collaborative features, we design a user–item bipartite graph with time-series review information and ratings as its edges, and then use the graph attention and different gating mechanisms to extract the corresponding features. To make full use of the limited interaction between the users and items, we use the contrastive learning paradigm for the nodes and edges in the bipartite graph to more effectively model the user–item interaction. A large number of experiments on five public data from Amazon prove that the performance of the GANCL is improved by 2.76% and 2.83% respectively compared with the state-of-the-art algorithms in MSE and MAE.

Graph neural networks with deep mutual learning for designing multi-modal recommendation systems

Recommendation services play a pivotal role in financial decision-making and multimedia content services, as they suggest investment operations and personalized items to users, typically characterized by multi-modal features such as visual, textual, and acoustic attributes. Graph Neural Networks (GNNs), demonstrating the immense potential for graph representation learning and recommendation systems, are capable of learning user/item embeddings by taking into account the graph topological structure and the multi-modal node features. Yet, a substantial number of multi-modal recommendation studies have seemingly ignored the inherent bias among different modalities during feature fusion, consequently leading to sub-optimal embeddings for items with multi-modal features. To mitigate this issue, we propose a novel multi-modal recommendation framework that integrates GNNs with deep mutual learning techniques, termed GNNMR. GNNMR uses the mutual knowledge distillation technique to collaboratively train multiple uni-modal bipartite user-item graphs. Each GNN is trained specifically on the uni-modal user-item bipartite graph, which is separated from the original multi-modal user-item bipartite graph, to generate uni-modal embeddings. These uni-modal embeddings then act as mutual supervision signals, allowing the model to uncover and synchronize the latent semantic relationships among different modalities. Subsequently, the model can conduct inference in an ensemble manner, leveraging uni-modal embeddings from diverse modalities. Experimental results on two real-world datasets demonstrate that the proposed GNNMR outperforms other multi-modal recommendation methods in the Top-K recommendation task.

A Reinforcement Learning List Recommendation Model Fused with Graph Neural Networks

Existing list recommendation methods present a list consisting of multiple items for feedback recommendation to user requests, which has the advantages of high flexibility and direct user feedback. However, the structured representation of state data limits the embedding of users and items, making them isolated from each other, missing some useful infomation for recommendation. In addition, the traditional non-end-to-end learning series takes a long time and accumulates errors. During the model training process, the results of each task can easily affect the next calculation, thus affecting the entire training effect. Aiming at the above problems, this paper proposes a Reinforcement Learning List Recommendation Model Fused with a Graph Neural Network, GNLR. The goal of this model is to maximize the recommendation effect while ensuring that the list recommendation system accurately analyzes user preferences to improve user experience. To this end, firstly, we use an user–item bipartite graph and Graph Neural Network to aggregate neighborhood information for users and items to generate graph structured representation; secondly, we adopt an attention mechanism to assign corresponding weights to neighborhood information to reduce the influence of noise nodes in heterogeneous information networks; finally, we alleviate the problems of traditional non-end-to-end methods through end-to-end training methods. The experimental results show that the method proposed in this paper can alleviate the above problems, and the recommendation hit rate and accuracy rate increase by about 10%.

Learning from Hierarchical Structure of Knowledge Graph for Recommendation

Knowledge graphs (KGs) can help enhance recommendations, especially for the data-sparsity scenarios with limited user-item interaction data. Due to the strong power of representation learning of graph neural networks (GNNs), recent works of KG-based recommendation deploy GNN models to learn from both knowledge graph and user-item bipartite interaction graph. However, these works have not well considered the hierarchical structure of knowledge graph, leading to sub-optimal results. Despite the benefit of hierarchical structure, leveraging it is challenging since the structure is always partly-observed. In this work, we first propose to reveal unknown hierarchical structures with a supervised signal detection method and then exploit the hierarchical structure with disentangling representation learning. We conduct experiments on two large-scale datasets, of which the results well verify the superiority and rationality of the proposed method. Further experiments of ablation study with respect to key model designs have demonstrated the effectiveness and rationality of our proposed model. The code is available at https://github.com/tsinghua-fib-lab/HIKE .

BLoG: Bootstrapped graph representation learning with local and global regularization for recommendation

With the explosive growth of online information, the significant application value of recommender systems has received considerable attention. Since user–item interactions can naturally fit into graph structure data, graph neural networks (GNNs), by virtue of their strong ability in graph representation learning, have become the new state-of-the-art approach to recommender systems. Recently, GNN-based contrastive self-supervised learning (SSL) methods have received careful attention due to their superiority over graph-based recommendation under the typical supervised learning paradigm. However, to achieve state-of-the-art performance, GNN-based recommendation with SSL often needs a huge amount of negative examples and the model’s performance is heavily dependent on complex data augmentations. Also, the information interaction among various augmented views is often performed under a single perspective (e.g., structure/feature space or node/graph level). In this paper, we propose a novel bootstrapped graph representation learning with local and global regularization for recommendation, i.e., BLoG, which constructs positive/negative pairs based on the aggregated node features by referring to two alternate views of the original user–item graph structure. In particular, BLoG learns user–item representations by encoding two augmented versions of a user–item bipartite graph using two separate encoders: an online encoder and a target encoder. To facilitate the information interaction between these two distinct graph encoders, we introduce local and global regularization for recommendation, where a graph structural contrastive loss and a node-level semantic loss are defined for local regularization while a graph-level contrastive loss is used for global regularization. An alternative optimization approach is used to train the online encoder and the target encoder. Experimental studies on three benchmark datasets demonstrate that BLoG achieves better recommendation accuracy than several existing baselines.

Modeling multi-attribute and implicit relationship factors with self-supervised learning for recommender systems

Interactions of users and items can be naturally modeled as a user-item bipartite graph in recommender systems, and emerging research is devoted to exploring user-item graphs for collaborative filtering methods. In reality, user-item interaction usually stems from more complex underlying factors, such as the users’ specific preferences. A user-item bipartite graph could be used to understand the differences in motivation. However, existing research has not clearly proposed and modeled the factors that affect the differences, ignoring the similarities between user pairs and item pairs, preventing them from capturing fine-grained user preferences more effectively. In addition to the two points mentioned above, most GNN-based models for recommendation have the following two limitations: First, the model’s accuracy depends on the number of observed interactions in the dataset. Secondly, node representations are vulnerable to noisy interactions. This work has developed a novel recommendation model called “Multi-Attribute and Implicit Relationship Factors With Self-Supervised Learning for Collaborative filtering” (MIS-CF), which explicitly proposes and models multi-attribute and implicit relationship factors for collaborative filtering recommendation. Meanwhile, an auxiliary self-supervised learning task is designed to help the downstream task optimize the node representation. MIS-CF aggregates multi-attribute spaces through the user-item bipartite graph and establishes user-user and item-item graphs to model the similar relationship information of neighbor pairs through a memory model. The self-supervised learning task generates contrastive learning via self-discrimination, thus mining the rich auxiliary signals within the data, improving the accuracy and robustness of our model. Moreover, the sparse regularizer is utilized to alleviate the overfitting problem. Extensive experimental results on three public datasets not only show the significant performance and robustness gain of the proposed model but also prove the effectiveness and interpretability of fine-grained implicit factors modeling.

Dual attentive graph convolutional networks for cross-domain recommendation

Cross-domain recommendation aims to alleviate the target domain’s data sparsity problem by leveraging source domain knowledge. Existing GCN-based approaches perform graph convolution operations in each domain separately. However, the direct effect of item feature and topological structure information in the source domain are neglected for user preference modeling in the target domain. In this paper, we propose a novel Dual Attentive Graph Convolutional Network for Cross-Domain Recommendation (DAG4CDR). Specifically, we integrate the source and target domain’s interaction data to construct a unified user-item bipartite graph and then perform GCN propagation on the graph to learn user and item embeddings. Over the unified graph, the interaction data from both domains can be leveraged to learn user and item embeddings via information propagation. In the embedding aggregation phase, the messages passed from different items of two domains to users are weighted by a designed dual attention mechanism, which considers the contributions of different items from both node- and domain-level. We conducted extensive experiments to validate the effectiveness of our method on several publicly available datasets, and the results demonstrate the superiority of our model on preference modeling for both common and non-common users.

Effective Community Search on Large Attributed Bipartite Graphs

Community search over bipartite graphs has attracted significant interest recently. In many applications such as the user–item bipartite graph in e-commerce and customer–movie bipartite graph in movie rating website, nodes tend to have attributes. However, the previous community search algorithms on bipartite graphs ignore attributes, thus making them to return results with poor cohesion with respect to their node attributes. In this paper, we study the community search problem on attributed bipartite graphs. Given a query vertex [Formula: see text], we aim to find the attributed [Formula: see text]-communities of [Formula: see text], where the structure cohesiveness of the community is described by the [Formula: see text]-core model, and the attribute similarity of two groups of nodes in the subgraph is maximized. In order to retrieve attributed communities from bipartite graphs, we first propose a basic algorithm composed of two steps: the generation and verification of candidate keyword sets, and then two improved query algorithms Inc and Dec are proposed. Inc is proposed considering the anti-monotonicity property of attributed bipartite graphs, then we adopt different generating methods and verify the order of candidate keyword sets and propose the Dec algorithm. After evaluating our solutions on eight large graphs, the experimental results demonstrate that our methods are effective and efficient in querying the attributed communities on bipartite graphs.

XSimGCL: Towards Extremely Simple Graph Contrastive Learning for Recommendation

Contrastive learning (CL) has recently been demonstrated critical in improving recommendation performance. The underlying principle of CL-based recommendation models is to ensure the consistency between representations derived from different graph augmentations of the user-item bipartite graph. This self-supervised approach allows for the extraction of general features from raw data, thereby mitigating the issue of data sparsity. Despite the effectiveness of this paradigm, the factors contributing to its performance gains have yet to be fully understood. This paper provides novel insights into the impact of CL on recommendation. Our findings indicate that CL enables the model to learn more evenly distributed user and item representations, which alleviates the prevalent popularity bias and promoting long-tail items. Our analysis also suggests that the graph augmentations, previously considered essential, are relatively unreliable and of limited significance in CL-based recommendation. Based on these findings, we put forward an e <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">X</b> tremely <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Sim</b> ple <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">C</b> ontrastive <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">L</b> earning method ( <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">XSimGCL</b> ) for recommendation, which discards the ineffective graph augmentations and instead employs a simple yet effective noise-based embedding augmentation to generate views for CL. A comprehensive experimental study on four large and highly sparse benchmark datasets demonstrates that, though the proposed method is extremely simple, it can smoothly adjust the uniformity of learned representations and outperforms its graph augmentation-based counterparts by a large margin in both recommendation accuracy and training efficiency. The code and used datasets are released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Coder-Yu/SELFRec</uri> .

A Graph Convolution Collaborative Filtering Integrating Social Relations Recommendation Method

Traditional collaborative filtering recommendation algorithms only consider the interaction between users and items leading to low recommendation accuracy. Aiming to solve this problem, a graph convolution collaborative filtering recommendation method integrating social relations is proposed. Firstly, a social recommendation model based on graph convolution representation learning and general collaborative filtering (SRGCF) is constructed; then, based on this model, a social relationship recommendation algorithm (SRRA) is proposed; secondly, the algorithm learns the representations of users and items by linear propagation on the user–item bipartite graph; then the user representations are updated by learning the representations with social information through the neighbor aggregation operation in the social network to form the final user representations. Finally, the prediction scores are calculated, and the recommendation list is generated. The comparative experimental results on four real-world datasets show that: the proposed SRRA algorithm performs the best over existing baselines on Recall@10 and NDCG@10; specifically, SRRA improved by an average of 4.40% and 9.62% compared to DICER and GraphRec, respectively, which validates that the proposed SRGCF model and SRRA algorithm are reasonable and effective.

Supervised contrastive learning for recommendation

In the recommendation system, collaborative filtering methods based on the graph convolution network can explicitly model the interaction between the nodes of the user–item bipartite graph and effectively use higher-order neighbor information. However, its representations are very susceptible to the noise of interaction. In response to this problem, SGL explored the self-supervised learning on the user–item graph to improve the robustness of GCN. Nevertheless, the contrastive learning framework it applied does not consider the specificity of the recommendation task and the uncertainty of user–item interaction fully.In order to solve the above problems, we propose a learning paradigm called supervised contrastive learning (SCL) based on the graph convolutional neural network. We carefully design SCL guided by the basic idea of the recommendation task that users with similar interaction histories have similar interests and preferences. Specifically, we will calculate the similarity between different nodes on the user side and the item side respectively during data preprocessing firstly. And then when applying contrastive learning, not only will the augmented samples be regarded as the positive samples, but also a certain number of augmented samples of similar nodes will be regarded as the positive samples, which is different with SGL that treats other samples in a batch as negative samples. SCL purposefully makes representations learned by similar nodes close to each other in the feature space. In addition, to address the uncertainty of node interaction, we also propose a new data augment method called node replication. We apply SCL on the most advanced LightGCN. Empirical research and ablation study on Gowalla, Yelp2018, and Amazon-Book datasets prove the effectiveness, accuracy, and robustness of SCL and node replication.

REDRL: A review-enhanced Deep Reinforcement Learning model for interactive recommendation

Recent advances in interactive recommender systems (IRS) have received wide attention due to its flexible recommendation strategy and optimization for users’ long-term utility. Considering this interaction paradigm of IRS, researchers have made some attempts to incorporate reinforcement learning (RL) models into IRS, because of the excellent ability of RL in long-term optimizing and decision making. However, data sparsity is an intractable problem most IRS urgently need to address. Although a small amount of work has exploited reviews to address data sparsity, they ignored the varying importance of items for modeling the user. In addition, most existing RL-based approaches suffer from decision-making difficulties when the action space becomes large. To solve above problems, in this work, we present a Review-enhanced Deep Reinforcement Learning model (REDRL) for interactive recommendation. Specifically, we utilize text reviews, combined with a pretrained review representation model to acquire item review-enhanced embedding representations. Then we formalize the recommendation problem as a Markov Decision Process (MDP), and exploit deep reinforcement learning (DRL) to model the interactive recommendation. Notably, we introduce a multi-head self-attention technique to capture distinct importance of various items in the sequence behavior, which is overlooked by existing work when modeling the user preference. In this way, we can model long-term dynamic preferences of users accurately and discriminately for comprehensive interactive recommendation. Moreover, we subtly combine the semantic structure information in the user–item bipartite graph with meta-paths in heterogeneous information networks (HIN), to filter some irrelevant items and obtain candidate items dynamically. By this means, the size of the discrete action space is effectively reduced from a new anger. The experimental results based on three benchmark datasets demonstrate the efficiency of our method with significant improvement over state-of-the-art.

Knowledge Graph Recommendation Model Based on Feature Space Fusion

The existing recommendation model based on a knowledge graph simply integrates the behavior features in a user–item bipartite graph and the content features in a knowledge graph. However, the difference between the two feature spaces is ignored. To solve this problem, this paper presents a new recommendation model named the knowledge graph recommendation model based on feature space fusion (KGRFSF). Specifically, in the behavioral feature space, the behavioral features of users and items are constructed by extracting the behavioral feature from the user–item bipartite graph. In the content feature space, the content features related to users and items are extracted through the attention mechanism on the knowledge graph, and then the content feature vectors of users and items are constructed. Finally, through the feature space fusion model, the behavior features and content features are projected into the same preference feature space, and then the fusion of the two feature spaces is completed to construct the complete vector representations of users and items and calculate the vector similarity to predict the score of the user to the item. This paper applies the presented model to public datasets in the fields of music and film. It can be found through the experimental results that KGRFSF can effectively improve the recommendation accuracy compared with the existing models.

Low-Pass Graph Convolutional Network for Recommendation

Spectral graph convolution is extremely time-consuming for large graphs, thus existing Graph Convolutional Networks (GCNs) reconstruct the kernel by a polynomial, which is (almost) fixed. To extract features from the graph data by learning kernels, Low-pass Collaborative Filter Network (LCFN) was proposed as a new paradigm with trainable kernels. However, there are two demerits of LCFN: (1) The hypergraphs in LCFN are constructed by mining 2-hop connections of the user-item bipartite graph, thus 1-hop connections are not used, resulting in serious information loss. (2) LCFN follows the general network structure of GCNs, which is suboptimal. To address these issues, we utilize the bipartite graph to define the graph space directly and explore the best network structure based on experiments. Comprehensive experiments on two real-world datasets demonstrate the effectiveness of the proposed model. Codes are available on https://github.com/Wenhui-Yu/LCFN.

HNF: Hybrid Neural Filtering Based on Centrality-Aware Random Walk for Personalized Recommendation

Social computing which analyzes users’ behaviors can help personalized recommender system to extract preferences of users. Most of personalized recommender systems exploit a user-item rating matrix to learn representations of users and items for predicting users’ ratings on items. In this paper, we design a new framework, called HNF, to learn two kinds of representations and fuse them for recommendation. Our HNF consists of a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">topological neural filtering</i> (TNF) module, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">collaborative neural filtering</i> (CNF) module and prediction module. The TNF module is to learn topological representations of user-item interactions from a user-item bipartite graph constructed based on a user-item rating matrix. The CNF module is to learn collaborative representations of user-item interactions. The prediction module aims to fuse the topological representations and collaborative representations to generate hybrid representations for rating prediction. We conduct experiments on three real-world public datasets. Results validate that our proposed HNF algorithm outperforms the state-of-the-art algorithms in terms of higher evaluation metrics.

Graph Enhanced Neural Interaction Model for recommendation

Since user-item interactions in recommender systems can be naturally modeled as a bipartite graph, recent studies have started to incorporate graph neural networks (GNNs) to learn user and item representations. However, existing GNN-based models for recommendation usually emphasize the graph structure but neglect the rich node (i.e., users and items) features or linearly integrate the node features without considering the interactions among these features, which leads to a suboptimal recommendation model. Considering the features (e.g., categorical features) are often discrete, sparse, and high-dimensional, how to jointly utilize the graph structure and node features while considering the feature interactions is a major challenge. In this paper, we propose Graph Enhanced Neural Interaction Model (GENIM), a novel graph recommendation model consisting of three parts: (1) graph convolution layers that recursively propagate the encoded node features on the user-item bipartite graph; (2) the neural feature interaction layer that learns node feature interactions, which contains rich signals for predictive analytics; (3) an optional hashing-based embedding layer that is used to reduce the model size. Extensive experiments conducted on two real-world datasets show that our model outperforms other state-of-the-art solutions.

RGCF: Refined graph convolution collaborative filtering with concise and expressive embedding

Graph Convolution Networks (GCNs) have attracted significant attention and have become the most popular method for learning graph representations. In recent years, many efforts have focused on integrating GCNs into recommender tasks and have made remarkable progress. At its core is to explicitly capture the high-order connectivities between nodes in the user-item bipartite graph. However, we found some potential drawbacks existed in the traditional GCN-based recommendation models are that the excessive information redundancy yield by the nonlinear graph convolution operation reduces the expressiveness of the resultant embeddings, and the important popularity features that are effective in sparse recommendation scenarios are not encoded in the embedding generation process. In this work, we develop a novel GCN-based recommendation model, named Refined Graph convolution Collaborative Filtering (RGCF), where a refined graph convolution structure is designed to match non-semantic ID inputs. In addition, a new fine-tuned symmetric normalization is proposed to mine node popularity characteristics and further incorporate the popularity features into the embedding learning process. Extensive experiments were conducted on three public million-size datasets, and the RGCF improved by an average of 13.45% over the state-of-the-art baseline. Further comparative experiments validated the effectiveness and rationality of each part of our proposed RGCF. We released our code at https://github.com/hfutmars/RGCF.

A Community-Driven Deep Collaborative Approach for Recommender Systems

Recommender systems (RS) are increasingly leveraging the power of graphs to enhance accuracy. However, we stipulate that existing methods don’t take into consideration the inherent behavior of communities and the interaction between all the sub-groups of the network. In this work, we develop a Deep Graph-based Collaborative Filtering recommender system (DGCF), which incorporates the concept of community profiling and leverages the power of Graph Neural Networks. DGCF utilizes multiple graphs to exploit all types of information from the different user interactions. It extracts the overlapping communities from the homophily user-user graph and also integrates the high-order information from the user-item bipartite graph. We conduct experiments and evaluate the DGCF on the MovieLens datasets(ML-100K and ML-1M), and Douban dataset. Our experiments reveal significant improvements over a number of the latest deep learning models for recommender systems. Results also support that DGCF has the potential to render better recommendations as it extracts deep relationships using the community structure.

HS-GCN: Hamming Spatial Graph Convolutional Networks for Recommendation

An efficient solution to the large-scale recommender system is to represent users and items as binary hash codes in the Hamming space. Towards this end, existing methods tend to code users by modeling their Hamming similarities with the items they historically interact with, which are termed as the first-order similarities in this work. Despite their efficiency, these methods suffer from the suboptimal representative capacity, since they forgo the correlation established by connecting multiple first-order similarities, i.e., the relation among the indirect instances, which could be defined as the high-order similarity. To tackle this drawback, we propose to model both the first- and the high-order similarities in the Hamming space through the user-item bipartite graph. Therefore, we develop a novel learning to hash framework, namely Hamming Spatial Graph Convolutional Networks (HS-GCN), which explicitly models the Hamming similarity and embeds it into the codes of users and items. Extensive experiments on three public benchmark datasets demonstrate that our proposed model significantly outperforms several state-of-the-art hashing models, and obtains performance comparable with the real-valued recommendation models.