Matrix factorization with dual-network collaborative embedding for social recommendation

The appearance and growth of social networking brings an exponential growth of information. One of the main solutions proposed for this information overload problem are recommender systems, which provide personalized results. Most existing social recommendation approaches consider relation information to improve recommendation performance in the static context. However, relations are likely to evolve over time in the dynamic network. Therefore, temporal information is an essential ingredient to making social recommendation. In this paper, we propose a novel social recommendation model based on evolving relation network, named SoERec. The learned evolving relation network is a heterogeneous information network, where the strength of relation between users is a sum of the influence of all historical events. We incorporate temporally evolving relations into the recommendation algorithm. We empirically evaluate the proposed method on two widely-used datasets. Experimental results show that the proposed model outperforms the state-of-the-art social recommendation methods.

Recommender systems based on multiple social networks correlation

Recommender systems try to propose a list of main interests of an on line social network user based on his predicted rating values. In the recent years, several methods are proposed such as Interest Social Recommendation method (ISoRec), and Social Recommendation method based on trust Sequence Matrix Factorization which employs matrix factorization techniques to address the trust propagation and sequential behaviors issues. Main drawback of these works is that they ignore implicit interest of users. Therefore, the main goal of this paper is to solve user-item rating based on the trust, sequential interest and the implicit interest of users, simultaneously. In order to solve this problem, our proposed method combines these parameters as its inputs. This method based on matrix factorization named as ISoTrustSeq. Experimental results show higher accuracy of predicted values in compared to the above-mentioned methods. Our results are also much better than these methods in terms of variation in the number of user-items features.

The recommender system is of great significance to alleviate information overload. The rise of online social networks leads to a promising direction—social recommendation. By injecting the interaction influence among social users, recommendation performance has been further improved. Successful as they are, we argue that most social recommendation methods are still not sufficient to make full use of social network information. Existing solutions typically either considered only the local neighbors or treat neighbors’ information equally, even or both. However, few studies have attempted to solve these social recommendation problems jointly from both the perspective of social depth and social strength. Recently, graph convolutional neural networks have shown great potential in learning graph data by modeling the information propagation and aggregation process. Thus, we propose an attention-based social aggregation neural networks (abbreviated as SAN) model to build a recommendation system. Different from previous work, our proposed SAN model simulates the recursive social aggregation process to spread the global social influence, and simultaneously introduces social attention mechanism to incorporate the heterogeneous influences for better model user embedding. Instead of a shallow linear interaction function, we adopt multi-layer perception to model the complex user–item interaction. Extensive experiments on two real-world datasets show the effectiveness of our proposed model SAN, and further analysis verifies the generalization and flexibility of the model.

Since the invention of word2vec, the skip-gram model has significantly advanced the research of network embedding, such as the recent emergence of the DeepWalk, LINE, PTE, and node2vec approaches. In this work, we show that all of the aforementioned models with negative sampling can be unified into the matrix factorization framework with closed forms. Our analysis and proofs reveal that: (1) DeepWalk empirically produces a low-rank transformation of a network's normalized Laplacian matrix; (2) LINE, in theory, is a special case of DeepWalk when the size of vertices' context is set to one; (3) As an extension of LINE, PTE can be viewed as the joint factorization of multiple networks' Laplacians; (4) node2vec is factorizing a matrix related to the stationary distribution and transition probability tensor of a 2nd-order random walk. We further provide the theoretical connections between skip-gram based network embedding algorithms and the theory of graph Laplacian. Finally, we present the NetMF method as well as its approximation algorithm for computing network embedding. Our method offers significant improvements over DeepWalk and LINE for conventional network mining tasks. This work lays the theoretical foundation for skip-gram based network embedding methods, leading to a better understanding of latent network representation learning.

Recommender systems are powerful tools that filter and recommend content/information relevant to a given user. Collaborative filtering is the most popular technique used in building recommender systems and it has been successfully incorporated in many applications. These conventional recommendation systems require a minimum number of users, items, and ratings in order to provide effective recommendations. This results in the infamous cold-start problem where the system is not able to produce effective recommendations for new users. Recently, there has been an escalation in the popularity and usage of social networks, which persuades people to share their experiences in the form of reviews and ratings on social media. The components of social media such as the influence of friends, interests, and enjoyment create the opportunities to develop solutions for sparsity and cold start problems of recommendation systems. This paper aims to observe these patterns and analyze three of the existing social recommendation systems, SocialMF, SocialFD, and GraphRec. SocialMF and SocialFD algorithms are based on matrix factorization and distance metric learning respectively whereas GraphRec is an attention based deep learning model. Through extensive experimentation with the datasets that these algorithms were tested on and one new dataset, we compared the results based on evaluation metrics including Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). To investigate how trust impacts the performance of these models, we evaluated them by modifying the trust and social component. Experimental results show that there is no conclusive evidence that trust propagation plays a major part in these models. Moreover, these models show a slightly improved performance in the absence of trust statements.

Social recommendation utilizes social relations to extract auxiliary collaborative signals, effectively mitigating data sparsity issues. However, existing approaches predominantly focus on static influence from social friends while neglecting two critical aspects: the dynamic contextual patterns in user behaviors and the potential of collaborative users. To address these limitations and further alleviate data sparsity, we propose a context-aware dual graph attention network (CDGA) that simultaneously captures users’ static and dynamic interests through social relations and interaction records. The proposed CDGA model introduces a dynamic activation mechanism to simulate contextual influences, generating dynamic embeddings for users and items. Furthermore, we develop an adaptive fusion mechanism that integrates interaction channels across static and dynamic embeddings for interaction prediction. Extensive experiments on three benchmark datasets demonstrate that CDGA consistently outperforms state-of-the-art social recommendation methods, confirming its effectiveness.

Social recommendation, which utilizes social relations to enhance recommender systems, has been gaining increasing attention recently with the rapid development of online social network. Existing social recommendation methods are based on the fact that users preference or decision is influenced by their social friends' behaviors. However, they assume that the influences of social relation are always the same, which violates the fact that users are likely to share preference on diverse products with different friends. In this paper, we present a novel CSR (short for Characterized Social Regularization) model by designing a universal regularization term for modeling variable social influence. Our proposed model can be applied to both explicit and implicit iteration. Extensive experiments on a real-world dataset demonstrate that CSR significantly outperforms state-of-the-art social recommendation methods.

Social recommendation leverages social information to solve data sparsity and cold-start problems in traditional collaborative filtering methods. However, most existing models assume that social effects from friend users are static and under the forms of constant weights or fixed constraints. To relax this strong assumption, in this paper, we propose dual graph attention networks to collaboratively learn representations for two-fold social effects, where one is modeled by a user-specific attention weight and the other is modeled by a dynamic and context-aware attention weight. We also extend the social effects in user domain to item domain, so that information from related items can be leveraged to further alleviate the data sparsity problem. Furthermore, considering that different social effects in two domains could interact with each other and jointly influence user preferences for items, we propose a new policy-based fusion strategy based on contextual multi-armed bandit to weigh interactions of various social effects. Experiments on one benchmark dataset and a commercial dataset verify the efficacy of the key components in our model. The results show that our model achieves great improvement for recommendation accuracy compared with other state-of-the-art social recommendation methods.

Event-based social networks (EBSNs) provide convenient online platforms for users to organize, attend and share social events. Understanding users’ social influences in social networks can benefit many applications, such as social recommendation and social marketing. In this paper, we focus on the problem of predicting users’ social influences on upcoming events in EBSNs. We formulate this prediction problem as the estimation of unobserved entries of the constructed user-event social influence matrix, where each entry represents the influence value of a user on an event. In particular, we define a user’s social influence on a given event as the proportion of the user’s friends who are influenced by him/her to attend the event. To solve this problem, we present a combined collaborative filtering model, namely, Matrix Factorization with Event Neighborhood (MF-EN) model, by incorporating event-based neighborhood method into matrix factorization. Due to the fact that the constructed social influence matrix is very sparse and the overlap values in the matrix are few, it is challenging to find reliable similar event neighbors using the widely adopted similarity measures (e.g., Pearson correlation and Cosine similarity). To address this challenge, we propose an additional information based neighborhood discovery (AID) method by considering three event-specific features in EBSNs. The parameters of our MF-EN model are determined by minimizing the associated regularized squared error function through stochastic gradient descent. We conduct a comprehensive performance evaluation on real-world datasets collected from DoubanEvent. Experimental results demonstrate the superiority of the proposed model compared to several alternatives.

Social influence is essential to social recommendation. Current influence-based social recommendation focuses on the explicit influence on observed social links. However, in real cases, implicit social influence can also impact users' preference in an unobserved way. In this work, we concern two kinds of implicit influence: Local Implicit Influence of persons on unobserved interpersonal relations, and Global Implicit Influence of items broadcasted to users. We improve the state-of-the-art GNN-based social recommendation methods by modeling two kinds of implicit influences separately. Local implicit influence is involved by predicting unobserved social relationships. Global implicit influence is involved by defining global popularity of each item and personalize the impact of the popularity on each user. In a GCN network, explicit and implicit influence are integrated to learn the social embedding of users and items in social recommendation. Experimental results on Yelp initially demonstrate the effectiveness of proposed model.

Research of social recommendation aims at exploiting social information to improve the quality of a recommender system. It can be further divided into two classes. Explicit social recommendation assumes the existence of not only the users’ ratings on items, but also the explicit social connections between users. Implicit social recommendation assumes the availability of only the ratings but not the social connections between users, and attempts to infer implicit social connections between users with the goal to boost recommendation accuracy. This paper proposes a unified framework that is applicable to both explicit and implicit social recommendation. We propose an optimization framework to learn the degree of social correlation and rating prediction jointly, so these two tasks can mutually boost the performance of each other. Furthermore, a well-known challenge for implicit social recommendation is that it takes quadratic time to learn the strength of pairwise connections. This paper further proposes several practical tricks to reduce the complexity of our model to be linear to the observed ratings. The experiments show that the proposed model, with only two parameters, can significantly outperform the state-of-the-art solutions for both explicit and implicit social recommender systems.

In recent years, more and more recommendation algorithm considers social information. However, in the existing social recommendation algorithm focused on the rating prediction task, the user's rating bias and the item's rating bias are often not considered. Besides, the existing social recommendation algorithms usually fail to deal with the sparse problem of social information. Concerning the problem of ignores rating bias and social information sparsity in the social recommendation, this paper proposes a novel recommendation model that combines implicit information and rating bias based on the traditional matrix factorization model. The social information used includes explicit social information and implicit social information generated by collaborative user network embedding methods. Experimental results on two real public datasets show that compared with other recommendation models, the proposed model reduces 1.13% to 10.09% and 3.14% to 8.38% respectively in the Root Mean Square Error (RMSE) and the Mean Absolute Error (MAE). It shows that our proposed recommendation algorithm has a better recommendation effect.

Graph distance measures have emerged as an effective tool for evaluating the similarity or dissimilarity between graphs. Recently, there has been a growing trend in the application of movie networks to analyze and understand movie stories. Previous studies focused on computing the distance between individual characters in narratives and identifying the most important ones. Unlike previous techniques, which often relied on representing movie stories through single-layer networks based on characters or keywords, a new multilayer network model was developed to allow a more comprehensive representation of movie stories, including character, keyword, and location aspects. To assess the similarities among movie stories, we propose a methodology that utilizes a multilayer network model and layer-to-layer distance measures. We aim to quantify the similarity between movie networks by verifying two aspects: (i) regarding many components of the movie story and (ii) quantifying the distance between their corresponding movie networks. We tend to explore how five graph distance measures reveal the similarity between movie stories in two aspects: (i) finding the order of similarity among movies within the same genre, and (ii) classifying movie stories based on genre. We select movies from various genres: sci-fi, horror, romance, and comedy. We extract movie stories from movie scripts regarding character, keyword, and location entities to perform this. Then, we compute the distance between movie networks using different methods, such as the network portrait divergence, the network Laplacian spectra descriptor (NetLSD), the network embedding as matrix factorization (NetMF), the Laplacian spectra, and D-measure. The study shows the effectiveness of different methods for identifying similarities among various genres and classifying movies across different genres. The results suggest that the efficiency of an approach on a specific network type depends on its capacity to capture the inherent network structure of that type. We propose incorporating the approach into movie recommendation systems.

Network embedding approaches have recently attracted considerable interest as\nthey learn low-dimensional vector representations of nodes. Embeddings based on\nthe matrix factorization are effective but they are usually computationally\nexpensive due to the eigen-decomposition step. In this paper, we propose a\nRandom RangE FInder based Network Embedding (REFINE) algorithm, which can\nperform embedding on one million of nodes (YouTube) within 30 seconds in a\nsingle thread. REFINE is 10x faster than ProNE, which is 10-400x faster than\nother methods such as LINE, DeepWalk, Node2Vec, GraRep, and Hope. Firstly, we\nformulate our network embedding approach as a skip-gram model, but with an\northogonal constraint, and we reformulate it into the matrix factorization\nproblem. Instead of using randomized tSVD (truncated SVD) as other methods, we\nemploy the Randomized Blocked QR decomposition to obtain the node\nrepresentation fast. Moreover, we design a simple but efficient spectral filter\nfor network enhancement to obtain higher-order information for node\nrepresentation. Experimental results prove that REFINE is very efficient on\ndatasets of different sizes (from thousand to million of nodes/edges) for node\nclassification, while enjoying a good performance.\n