User-item Bipartite Graph Research Articles

Multi-Graph Heterogeneous Interaction Fusion for Social Recommendation

With the rapid development of online social recommendation system, substantial methods have been proposed. Unlike traditional recommendation system, social recommendation performs by integrating social relationship features, where there are two major challenges, i.e., early summarization and data sparsity. Thus far, they have not been solved effectively. In this article, we propose a novel social recommendation approach, namely Multi-Graph Heterogeneous Interaction Fusion (MG-HIF), to solve these two problems. Our basic idea is to fuse heterogeneous interaction features from multi-graphs, i.e., user–item bipartite graph and social relation network, to improve the vertex representation learning. A meta-path cross-fusion model is proposed to fuse multi-hop heterogeneous interaction features via discrete cross-correlations. Based on that, a social relation GAN is developed to explore latent friendships of each user. We further fuse representations from two graphs by a novel multi-graph information fusion strategy with attention mechanism. To the best of our knowledge, this is the first work to combine meta-path with social relation representation. To evaluate the performance of MG-HIF, we compare MG-HIF with seven states of the art over four benchmark datasets. The experimental results show that MG-HIF achieves better performance.

Dynamic evolution of multi-graph based collaborative filtering for recommendation systems

The recommendation system is an important and widely used technology in the era of Big Data. Current methods have fused side information into it to alleviate the sparsity problem, one of the key problems of recommendation systems. However, not all the side information can be obtained with high quality, and the specific methods based on side information are not universal. In addition, side information has not been mined by the existing graph-based methods. To address these problems, we propose a Dynamic evolution of Multi-Graph Collaborative Filtering (DMGCF) model to mine and reuse side information. Specifically, we first construct user graph and item graph based on user-item bipartite graph and embeddings to exploit inter-user and inter-item relationships. The two new graphs simulate side information in latent space. Next, we perform a dual-path graph convolution network (GCN) on these three graphs for collaborative filtering. Then, a novel dynamic evolution mechanism is proposed to update and promote the embeddings and graphs collaboratively during the learning process, which produces better embeddings, user and item relationships, as well as the rating scores. We conduct a series of experiments on real-world datasets, and experimental results show the effectiveness of our approach.

An ecommerce recommendation algorithm based on link prediction

In the field of ecommerce, most recommendation algorithms are based on user-item bipartite graph network (BGN). But this kind of recommendation algorithm is severely lacking in accuracy and diversity. In this paper, a novel ecommerce recommendation algorithm is proposed based on BGN link prediction. Firstly, all the user-item data were imported into distance formula to calculate the similarity between the attributes. Then, the BGN was projected into a single-mode network (SMN), making it more efficient to extract potential links from the BGN. On this basis, the potential links were predicted based on similarity. Through experiments on real ecommerce datasets, it was proved that our algorithm has a higher accuracy and coverage than typical recommendation algorithms.

Harnessing heterogeneous social networks for better recommendations: A grey relational analysis approach

Most of the extant studies in social recommender system are based on explicit social relationships, while the potential of implicit relationships in the heterogeneous social networks remains largely unexplored. This study proposes a new approach to designing a recommender system by employing grey relational analysis on the heterogeneous social networks. It starts with the establishment of heterogeneous social networks through the user-item bipartite graph, user social network graph and user-attribute bipartite graph; and then uses grey relational analysis to identify implicit social relationships, which are then incorporated into the matrix factorization model. Five experiments were conducted to test the performance of our approach against four state-of-the-art baseline methods. The results show that compared with the baseline methods, our approach can effectively alleviate the sparsity problem, because the heterogeneous social network provides richer information. In addition, the grey relational analysis method has the advantage of low requirements for data size and efficiently relieves the cold start problem. Furthermore, our approach saves processing time, thus increases recommendation efficiency. Overall, the proposed approach can effectively improve the accuracy of rating prediction in social recommendations and provide accurate and efficient recommendation service for users.

A review of recommendation system research based on bipartite graph

The interaction history between users and items is usually stored and displayed in the form of bipartite graphs. Neural network recommendation based on the user-item bipartite graph has a significant effect on alleviating the long-standing data sparseness and cold start of the recommendation system. The whole paper is based on the bipartite graph. An review of the recommendation system of graphs summarizes the three characteristics of graph neural network processing bipartite graph data in the recommendation field: interchangeability, Multi-hop transportability, and strong interpretability. The biggest contribution of the full paper is that it summarizes the general framework of graph neural network processing bipartite graph recommendation from the models with the best recommendation effect in the past three years: embedding layer, propagation update layer, and prediction layer. Although there are subtle differences between different models, they are all this framework can be applied, and different models can be regarded as variants of this general model, that is, other models are fine-tuned on the basis of this framework. At the end of the paper, the latest research progress is introduced, and the main challenges and research priorities that will be faced in the future are pointed out.

A Novel Intelligent Recommendation Algorithm Based on Mass Diffusion

Social recommendation algorithm is a common tool for recommending interesting or potentially useful items to users amidst the sea of online information. The users usually have various relationships, each of which has its unique impact on the recommendation results. It is unlikely to make accurate recommendations solely based on one relationship. Based on user-item bipartite graph, this paper establishes a multisubnet composited complex network (MSCCN) of multiple user relationships and then extends the mass diffusion (MD) algorithm into a novel intelligent recommendation algorithm. Two public online datasets, namely, Epinions and FilmTrust, were selected to verify the effect of the proposed algorithm. The results show that the proposed intelligent recommendation algorithm with two types of relationships made much more accurate recommendations than that with a single relationship and the traditional MD algorithm.

MGAT: Multimodal Graph Attention Network for Recommendation

Graph neural networks (GNNs) have shown great potential for personalized recommendation. At the core is to reorganize interaction data as a user-item bipartite graph and exploit high-order connectivity among user and item nodes to enrich their representations. While achieving great success, most existing works consider interaction graph based only on ID information, foregoing item contents from multiple modalities (e.g., visual, acoustic, and textual features of micro-video items). Distinguishing personal interests on different modalities at a granular level was not explored until recently proposed MMGCN (Wei et al., 2019). However, it simply employs GNNs on parallel interaction graphs and treats information propagated from all neighbors equally, failing to capture user preference adaptively. Hence, the obtained representations might preserve redundant, even noisy information, leading to non-robustness and suboptimal performance. In this work, we aim to investigate how to adopt GNNs on multimodal interaction graphs, to adaptively capture user preference on different modalities and offer in-depth analysis on why an item is suitable to a user. Towards this end, we propose a new Multimodal Graph Attention Network, short for MGAT, which disentangles personal interests at the granularity of modality. In particular, built upon multimodal interaction graphs, MGAT conducts information propagation within individual graphs, while leveraging the gated attention mechanism to identify varying importance scores of different modalities to user preference. As such, it is able to capture more complex interaction patterns hidden in user behaviors and provide a more accurate recommendation. Empirical results on two micro-video recommendation datasets, Tiktok and MovieLens, show that MGAT exhibits substantial improvements over the state-of-the-art baselines like NGCF (Wang, He, et al., 2019) and MMGCN (Wei et al., 2019). Further analysis on a case study illustrates how MGAT generates attentive information flow over multimodal interaction graphs.

Multi-Component Graph Convolutional Collaborative Filtering

The interactions of users and items in recommender system could be naturally modeled as a user-item bipartite graph. In recent years, we have witnessed an emerging research effort in exploring user-item graph for collaborative filtering methods. Nevertheless, the formation of user-item interactions typically arises from highly complex latent purchasing motivations, such as high cost performance or eye-catching appearance, which are indistinguishably represented by the edges. The existing approaches still remain the differences between various purchasing motivations unexplored, rendering the inability to capture fine-grained user preference. Therefore, in this paper we propose a novel Multi-Component graph convolutional Collaborative Filtering (MCCF) approach to distinguish the latent purchasing motivations underneath the observed explicit user-item interactions. Specifically, there are two elaborately designed modules, decomposer and combiner, inside MCCF. The former first decomposes the edges in user-item graph to identify the latent components that may cause the purchasing relationship; the latter then recombines these latent components automatically to obtain unified embeddings for prediction. Furthermore, the sparse regularizer and weighted random sample strategy are utilized to alleviate the overfitting problem and accelerate the optimization. Empirical results on three real datasets and a synthetic dataset not only show the significant performance gains of MCCF, but also well demonstrate the necessity of considering multiple components.

Graph-based Recommendation Meets Bayes and Similarity Measures

Graph-based approaches provide an effective memory-based alternative to latent factor models for collaborative recommendation. Modern approaches rely on either sampling short walks or enumerating short paths starting from the target user in a user-item bipartite graph. While the effectiveness of random walk sampling heavily depends on the underlying path sampling strategy, path enumeration is sensitive to the strategy adopted for scoring each individual path. In this article, we demonstrate how both strategies can be improved through Bayesian reasoning. In particular, we propose to improve random walk sampling by exploiting distributional aspects of items’ ratings on the sampled paths. Likewise, we extend existing path enumeration approaches to leverage categorical ratings and to scale the score of each path proportionally to the affinity of pairs of users and pairs of items on the path. Experiments on several publicly available datasets demonstrate the effectiveness of our proposed approaches compared to state-of-the-art graph-based recommenders.

Destructure-and-restructure matrix approximation

A matrix approximation is used to predict the missing values of a matrix, which has many applications in recommender systems. After predicting the missing values of a user-item rating matrix, we can recommend unrated items to a user according to their approximated values. This paper proposes a new approximation scheme for large and sparse global matrices, which is called a destructure-and-restructure matrix approximation. The basic idea is to first destructure a global matrix into many local matrices, and then restructure it from local matrix approximations. However, distance computation is a challenging issue in matrix destructure because no prior knowledge about the most appropriate feature vectors and distance measures are available. To deal with this issue, we propose a novel scheme that does not require any distance computation for local matrix construction, which is based on the application of convergence probabilities of a graph random walk. At first, a user-item bipartite graph is built from the global matrix. After performing random walk on the bipartite graph, we select several user-item pairs as anchors. Then, another random walk with restart is applied to construct local matrices from anchors. For each local matrix, we propose a weighted matrix factorization that is based on the rating distribution of the training data. In the restructure process, we first compute the approximation credibility of each local matrix, and we then finally obtain the global matrix approximation weighted from credible local approximations. Our experiments on five real-world datasets show that the proposed solution outperforms the state-of-the-art schemes in terms of lower prediction errors and higher coverage ratios.

Improved Metric-Based Recommender by Historical Interactions

A remarkable success in recommendations has been achieved by using methods based on metric learning, especially in digital marketing. However, the existing methods do not consider the relative preferences among items that users like. To overcome this issue, we propose an improved recommender model. First, the model analyses the user-item bipartite graph from historical interactions, and collects user-item similarities based on the topological features from this graph. Then, similar to other metric-based methods, both users and items are embedded as latent positions in a low-dimensional space, where users’ preferences on items are modelled as distances. Thus, we propose an improved metric-based recommender, i.e. the Graph Embedded Metric Factorisation recommender, under the assumptions that (1) the distance between a target user and an interacted-with item is determined by their topological similarity, and (2) for a target user, non-interacted items are located farther away than interacted-with ones. Comprehensive experiments on three practical datasets were implemented. Empirical results indicate that our improved recommender outperforms current state-of-the-art methods when making personalised recommendations based on users’ implicit feedback.

ANALYSIS OF COLLABORATIVE FILTERING WITH I-SSU RECOMMENDATION SYSTEM

Social recommendation is common and prosperous among varied urban property applications like merchandise recommendation, on-line sharing and looking services. Users build use of those applications to create many implicit social networks through their daily social interactions. The users in such social networks will rate some fascinating things and provides comments. the bulk of the present studies investigate the rating prediction and recommendation of things supported user-item bipartite graph and user-user social graph, therefore referred to as social recommendation. However, the spacial issue wasn't thought-about in their recommendation mechanisms. With the speedy development of the service of location-based social networks, the spacial info step by step affects the standard and correlation of rating and recommendation of things. This paper survey a location-based social network (LBSN) doesn't solely mean adding a location to Associate in Nursing existing social network so individuals within the social organisation will share location-embedded info, however conjointly consists of the new social organisation created from people connected by the interdependence derived from their a panorama of the recommendations locations within the physical world still as their location-tagged media content, like photos, videos and text. During this paper survey on in location-based social networks with a balanced depth, facilitating analysis into this rising topic.

A preference elicitation method based on bipartite graphical correlation and implicit trust

In the age of big data, information overload is getting worse. Most of the existing recommender systems which apply data analysis and behavioral analysis to make personal recommendation have suffered from the problem of low prediction accuracy. To address this problem, a new preference elicitation algorithm is developed by using bipartite graphical correlation and implicit trust. More precisely, to compute the bipartite graphical correlation, an improved single-source shortest path is firstly presented to get the shortest behavior path based on the user-item bipartite graph. While the Markov separation algorithm is employed to separate uncorrelated vertexes and obtain the values of bipartite graphical correlation. Secondly, the implicit trust is used to represent trust relationship between users and items which have no historical behaviors. Independent trust group is applied to represent the closed-loop path on the user-item bipartite graph, and a compute method is developed to get the values of implicit trust based on the trusty values of independent trust group and explicit trust. Finally, a weighted prediction method based on bipartite graphical correlation and implicit trust is employed to compute the final ratings. Our empirical experiments are performed on a sparse data set, the results of which have demonstrated that our method can achieve lower P@R and efficiently improve recommendation quality.

An Efficient Approach to Generating Location-Sensitive Recommendations in Ad-hoc Social Network Environments

Social recommendation has been popular and successful in various urban sustainable applications such as online sharing, products recommendation and shopping services. These applications allow users to form several implicit social networks through their daily social interactions. The users in such social networks can rate some interesting items and give comments. The majority of the existing studies have investigated the rating prediction and recommendation of items based on user-item bipartite graph and user-user social graph, so called social recommendation. However, the spatial factor was not considered in their recommendation mechanisms. With the rapid development of the service of location-based social networks, the spatial information gradually affects the quality and correlation of rating and recommendation of items. This paper proposes spatial social union (SSU), an approach of similarity measurement between two users that integrates the interconnection among users, items and locations. The SSU-aware location-sensitive recommendation algorithm is then devised. We evaluate and compare the proposed approach with the existing rating prediction and item recommendation algorithms subject to a real-life data set. Experimental results show that the proposed SSU-aware recommendation algorithm is more effective in recommending items with the better consideration of user’s preference and location.

Random walk models for top-N recommendation task

Recently there has been an increasing interest in applying random walk based methods to recommender systems. We employ a Gaussian random field to model the top-N recommendation task as a semi-supervised learning problem, taking into account the degree of each node on the user-item bipartite graph, and induce an effective absorbing random walk (ARW) algorithm for the top-N recommendation task. Our random walk approach directly generates the top-N recommendations for individuals, rather than predicting the ratings of the recommendations. Experimental results on the two real data sets show that our random walk algorithm significantly outperforms the state-of-the-art random walk based personalized ranking algorithm as well as the popular item-based collaborative filtering method.