Improving Recommendation Accuracy with Clustering-Based Social Regularization

Recent years, people have been gradually influenced by online socialization. The emergence and development of Graph Neural Networks (GNN) has shown great advantages in mining implicit data and expressing node relationships, etc. However, due to the arbitrary nature of establishing neighborly relationships, the judging reliability of trusting relationships between neighbors is a difficult issue. Therefore, this paper proposes an innovative approach to obtain the valid neighbor relationships based on real user-item interactions and friend trust relationships in the dataset. The proposed method can address the impact of invalid neighbors on the social model and achieve the effect of enhancing neighbor perception. For neighbor interaction in the graph neural network model, this paper establishes the direct connection between users and items through mapping of multilayer perceptron firstly. Then it integrates neighbor similarity and neighbor sampling to mitigate the interference information of invalid neighbors and achieves the effect of enhancing the perceived information of neighbor interaction. Finally, this paper establishes the item social space and user social space with enhanced neighbor perception according to the dyadic nature and organically integrated them to enrich the social data. Comparison experiments are carried out based on two publicly available datasets Epinions and Ciao, the recommended method performs better than other social recommendation models with the MAE and RMSE values being improved by 0.81%-1.09% and 1.15%-1.41% respectively.

Graph Neural Network(GNN) based social recommendation models improve the\nprediction accuracy of user preference by leveraging GNN in exploiting\npreference similarity contained in social relations. However, in terms of both\neffectiveness and efficiency of recommendation, a large portion of social\nrelations can be redundant or even noisy, e.g., it is quite normal that friends\nshare no preference in a certain domain. Existing models do not fully solve\nthis problem of relation redundancy and noise, as they directly characterize\nsocial influence over the full social network. In this paper, we instead\npropose to improve graph based social recommendation by only retaining the\ninformative social relations to ensure an efficient and effective influence\ndiffusion, i.e., graph denoising. Our designed denoising method is\npreference-guided to model social relation confidence and benefits user\npreference learning in return by providing a denoised but more informative\nsocial graph for recommendation models. Moreover, to avoid interference of\nnoisy social relations, it designs a self-correcting curriculum learning module\nand an adaptive denoising strategy, both favoring highly-confident samples.\nExperimental results on three public datasets demonstrate its consistent\ncapability of improving two state-of-the-art social recommendation models by\nrobustly removing 10-40% of original relations. We release the source code at\nhttps://github.com/tsinghua-fib-lab/Graph-Denoising-SocialRec.\n

Adaptive social recommendation combined with the multi-domain influence

In an era overwhelmed by academic big data, students grapple with identifying academic papers that resonate with their learning objectives and research interests, due to the sheer volume and complexity of available information. This study addresses the challenge by proposing a novel academic paper recommendation system designed to enhance personalized learning through the nuanced understanding of academic social networks. Utilizing the theory of social homogeneity, the research first constructs a sophisticated academic social network, capturing high-order social relationships, such as co-authorship and advisor–advisee connections, through hypergraph modeling and advanced network representation learning techniques. The methodology encompasses the development and integration of a hypergraph convolutional neural network and a contrastive learning framework to accurately model and recommend academic papers, focusing on aligning with students’ unique preferences and reducing reliance on sparse interaction data. The findings, validated across multiple real-world datasets, demonstrate a significant improvement in recommendation accuracy, particularly in addressing the cold-start problem and effectively mapping advisor–advisee relationships. The study concludes that leveraging complex academic social networks can substantially enhance the personalization and precision of academic paper recommendations, offering a promising avenue for addressing the challenges of academic information overload and fostering more effective personalized learning environments.

In the past few years, many companies are considering “ <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">social recommendation</i> ” for their businesses, e.g., firms are offering rewards to customers who recommend the firms’ products/services in online social networks (OSNs). However, the pros and cons of such social recommendation scheme are still unclear. Thus, it is difficult for firms to design rewarding schemes, and for OSN platforms to design regulating policies. By analyzing real data from Weixin and Yelp, we first identify key factors that affect the spreading of products/services in OSNs. These findings enable us to develop an accurate (i.e., with a high validation accuracy) mathematical model on social recommendations. Our model captures how users decide whether to recommend an item, which is a key factor but often ignored by previous social recommendation models such as the “ <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Independent Cascade model</i> ”. We also design algorithms to infer model parameters. Using our model, we uncover conditions when social recommendation improves a firm’s profit and users’ utilities, as well as when it cannot improve the profit or hurts users’ utilities. These conditions help the design of both rewarding schemes and regulating policies. Moreover, we extend our model to a dynamic setting, so that a firm can improve its profit by dynamically optimizing its rewarding schemes.

Social recommendation has been an active research topic over the last decade, based on the assumption that social information from friendship networks is beneficial for improving recommendation accuracy, especially when dealing with cold-start users who lack sufficient past behavior information for accurate recommendation. However, it is nontrivial to use such information, since some of a person's friends may share similar preferences in certain aspects, but others may be totally irrelevant for recommendations. Thus one challenge is to explore and exploit the extend to which a user trusts his/her friends when utilizing social information to improve recommendations. On the other hand, most existing social recommendation models are non-interactive in that their algorithmic strategies are based on batch learning methodology, which learns to train the model in an offline manner from a collection of training data which are accumulated from users? historical interactions with the recommender systems. In the real world, new users may leave the systems for the reason of being recommended with boring items before enough data is collected for training a good model, which results in an inefficient customer retention. To tackle these challenges, we propose a novel method for interactive social recommendation, which not only simultaneously explores user preferences and exploits the effectiveness of personalization in an interactive way, but also adaptively learns different weights for different friends. In addition, we also give analyses on the complexity and regret of the proposed model. Extensive experiments on three real-world datasets illustrate the improvement of our proposed method against the state-of-the-art algorithms.

Social recommendation, which aims to systematically leverage the social relationships between users as well as their past behaviors for automatic recommendation, attract much attention recently. The belief is that users linked with each other in social networks tend to share certain common interests or have similar tastes (homophily principle); such similarity is expected to help improve the recommendation accuracy and quality. There have been a few studies on social recommendations; however, they almost completely ignored the heterogeneity and diversity of the social relationship.In this paper, we develop a joint personal and social latent factor (PSLF) model for social recommendation. Specifically, it combines the state-of-the-art collaborative filtering and the social network modeling approaches for social recommendation. Especially, the PSLF extracts the social factor vectors for each user based on the state-of-the-art mixture membership stochastic blockmodel, which can explicitly express the varieties of the social relationship. To optimize the PSLF model, we develop a scalable expectation-maximization (EM) algorithm, which utilizes a novel approximate mean-field technique for fast expectation computation. We compare our approach with the latest social recommendation approaches on two real datasets, Flixter and Douban (both with large social networks). With similar training cost, our approach has shown a significant improvement in terms of prediction accuracy criteria over the existing approaches.

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.

Social recommendations introduce additional social information to capture users’ potential item preferences, thereby providing more accurate recommendations. However, friends do not always have the same or similar preferences, which means that social information is redundant and often biased for useritem interaction network. In addition, current social recommendation models focus on the item-level preferences, neglecting the critical fine-grained preference influence factors. To address these issues, we propose the Robust Preference-Guided based Disentangled Graph Social Recommendation (RPGD). First, we employ a graph neural network to adaptively convert the social network into a social preference network based on social information and user-item interaction information, reducing bias between social relationships and preference relationships. Then, we propose a self-supervised learning method that utilizes the social network to constrain and optimize the social preference network, thereby enhancing the stability of the network. Finally, we propose a method for disentangled preference representation to explore fine-grained preference influence factors, that enhance the performance of user and item representations. We conducted experiments on some open-source real-world datasets, and the results show that RPGD outperforms the SOTA performance on social recommendations. Our code is released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Andrewsama/RPGD-master</uri> .

In this paper, we propose SIR, a Social Item Recommendation model based on latent variable model and neighborhood model which effectively models the user interest similarities and social relationships in online social networks. We develop the learning algorithm for the parameter estimates of SIR. Furthermore, we construct an extended SIR model (SIR+) by taking the social interaction features into account to improve the performance of top-A item recommendation. The experiments on a real dataset from Sina Weibo, one of the most popular social network sites (SNS) in China, demonstrate that both SIR and SIR+ outperform the traditional collaborative filtering methods, and SIR+ achieves a better performance than SIR.

Recommender systems have been widely employed to suggest personalized online information to simplify users' information discovery process. With the popularity of online social networks, analysis and mining of social factors and social circles have been utilized to support more effective recommendations, but have not been fully investigated. In this chapter, the authors propose a novel recommendation model with the consideration of more comprehensive social factors and topics. To further enhance recommendation accuracy, four social factors are simultaneously injected into the recommendation model based on probabilistic matrix factorization. Meanwhile, the authors explore several new methods to measure these social factors. Moreover, they infer explicit and implicit social circles to enhance the performance of recommendation diversity. Finally, the authors conduct a series of experiments on publicly available data. Experimental results show the proposed model achieves significantly improved performance over the existing models in which social information have not been fully considered.

GNN-based social recommendation aims to use social network information to improve recommendation performance of traditional user–item interaction network (U–I network). However, in graph neural network information aggregation, both social networks and U–I networks inevitably have noise, which affects accuracy of recommendation results. To reduce the noise impact of network data, we propose Robust Social Recommendation based on Contrastive Learning and Dual-Stage Graph Neural Network (CLDS). First, considering instability of social networks, we propose the social preference network. It is robust and retains only social friend relationships with common preferences. Based on it and U–I network, we construct a social recommendation pre-training model. Next, we propose self-contrastive learning method. The method initializes multiple social network node representations through Gaussian distribution, pre-training and random disturbance, respectively. Then, it uses contrastive learning on the generated multiple node representations to enhance the robustness of node representation. Finally, CLDS avoids directly capturing potentially user–user and item–item information in U–I networks which is incomplete and untrusted. And instead, it only extracts user–item information to reduce the noise generated by GNN-based U–I network information aggregation. We conduct experiments under the open-source real network dataset. The experimental results show that CLDS outperforms state-of-art methods in social recommendation. The code is available at: https://github.com/Andrewsama/CLDS-master.

Classic collaborative filtering methods suffer from lack of accuracy when it comes to todays complicated ecommerce websites. Recommender systems can be more efficient and effective by considering each user behavior model individually and in groups with other people that can be interpreted as their social relations. This paper presents a new context aware and behavior-based recommender system which utilizes social network analysis to enhance recommending results. The general idea is extracting user behavior patterns in different context based on user's past interactions with the system for further classifications. In this study we use the idea of using social network analysis with an improvement; we consider multiple relations among users and use a multi-layer social network to make our groups of preferences richer. Different social network metrics such as centralization, modularity class and so on can help us find similar groups of users in social network. We combine all the results and suggest top-K items to the user based on his/her nearest neighbor opinions. Evaluating the results shown significant improvement in accuracy of recommendations for proposed approach in contrast to previous techniques.

Social recommendation, which seeks to leverage social ties among users to alleviate the sparsity issue of user-item interactions, has emerged as a popular technique for elevating personalized services in recommender systems. Despite being effective, existing social recommendation models are mainly devised for recommending regular items such as blogs, images, and products, and largely fail for community recommendations due to overlooking the unique characteristics of communities. Distinctly, communities are constituted by individuals, who present high dynamicity and relate to rich structural patterns in social networks. To our knowledge, limited research has been devoted to comprehensively exploiting this information for recommending communities.

Modeling user preferences using neural networks and tensor factorization model