Community-based social recommendation under local differential privacy protection

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> .

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.

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 based on multiple social networks correlation

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.

Frequent itemset mining is a basic data mining task and has many applications in other data mining tasks. However, it is likely that the user's personal privacy information may be leaked in the mining process. In recent years, applying the local differential privacy protection model to mine all frequent itemsets is a relatively reliable and secure protection method. In local differential privacy, users first perturb the original data then send it to the aggregator, which prevents the aggregator leaking user's private information throughout the process. There are two major problems with data mining using local differential privacy, one is that the accuracy of the results is relatively low after mining, and the other is that the user transmits too much data to the server, which results in higher communication costs. In this paper, we use Hadamard response algorithm to improve the accuracy of the results while reduce the communication cost. Finally, we use FP-tree for frequent itemset mining to compare the Hadamard response with previous algorithms.

Top-k frequent items detection is a fundamental task in data stream mining. Many promising solutions are proposed to improve memory efficiency while still maintaining high accuracy for detecting the Top-k items. Despite the memory efficiency concern, the users could suffer from privacy loss if participating in the task without proper protection, since their contributed local data streams may continually leak sensitive individual information. However, most existing works solely focus on addressing either the memory-efficiency problem or the privacy concerns but seldom jointly, which cannot achieve a satisfactory tradeoff between memory efficiency, privacy protection, and detection accuracy. In this paper, we present a novel framework HG-LDP to achieve accurate Top-k item detection at bounded memory expense, while providing rigorous local differential privacy (LDP) protection. Specifically, we identify two key challenges naturally arising in the task, which reveal that directly applying existing LDP techniques will lead to an inferior "accuracy-privacy-memory efficiency" tradeoff. Therefore, we instantiate three advanced schemes under the framework by designing novel LDP randomization methods, which address the hurdles caused by the large size of the item domain and by the limited space of the memory. We conduct comprehensive experiments on both synthetic and real-world datasets to show that the proposed advanced schemes achieve a superior "accuracy-privacy-memory efficiency" tradeoff, saving 2300× memory over baseline methods when the item domain size is 41,270. Our code is anonymously open-sourced via the link.

A survey of graph neural network based recommendation in social networks

SummaryIn big data mining, the K‐prototypes has become a popular clustering method for mixed data owing to its simplicity and efficiency. However, the data clustering process of the K‐prototypes method will cause the risk of user privacy leakage because user data usually contain sensitive information. To address this issue, general solutions introduce a trusted third‐party model for privacy protection in clustering analysis, but it is difficult to find a fully trusted entity in reality. In this article, we propose a local differential privacy K‐prototypes (LDPK) mechanism, which does not require any trusted third party to perform privacy preprocessing on user data. Our mechanism first uses local differential privacy to disturb user data, then completes the clustering through the interaction between server and user. Furthermore, we propose a privacy protection enhancement mechanism (ELDPK) by extending the LDPK mechanism, which disturbs the user's clustering information in each iteration to protect user privacy further. Theoretical analysis proves the privacy and feasibility of our proposed scheme, and the experimental results prove that our proposed scheme can guarantee the quality of the clustering results under the premise of satisfying the local differential privacy.

The purpose of this study is to explore the experience of the consultant’s usage on social-network and the subsequent decisions made To this end, the following four issues will be the focus of this research: the motivation and current state of the consultant’s usage on social networking sites; the consultant’s personal decision-making considerations on social networking sites; the challenges faced by the consultant on social networking sites; the consultant’s perspective on “the usage on social networking Accordingly, the research methods used will be purposive sampling and semi-structured in-depth interviews. First, six consultants would be invited to participate in the research on the usage for social networking sites. Next, the data collected through interviews would be organized, summarized and analyzed with grounded theory. Finally, the results of the study will be discussed comprehensively. Interviewee responses to the research questions: 1.The motivation and current state of the consultant’s usage on social networking The motivation for the respondents to apply for a social networking site is to interact with friends. The current state of the respondents’ usage on social networking can be summarized as follows: respondents who have long term experience in social networking will have more than one personal site; the direction of writing and the presentation of content, will be affected by the features of social networking sites, which also affects the relationship with the audience. Furthermore, the micro-blog type community site has become an integral part of the respondents’ lives. 2.Consultant’s personal decision-making considerations on the usage on social networking There are several considerations that factor into the consultants’ decisions when using the social networking sites: openness of the community site itself, ease of to spreading on the network, convenience for browsing, privacy of their own and others, personal confidentiality and protection of personal rights and interests. Furthermore, the potential ability of social networking to influence others is an important consideration for consultants due to their roles and responsibilities. 3.The challenges faced by the consultants on social networking (A)Respondents experienced negative emotions after prying into certain cases on social networking out of curiosity. (B)Respondents with the aforementioned experience tend to readjust their perspective and actions on social networking sites. 4.The consultant’s perspective on “the usage on social networking sites (A)Consultants should not be denied the right to use social networking due to their profession. However, consultants should use such with professional integrity. (B)The ability of consultants to understand the purpose of using social networking and the information to be conveyed would enable them to have a clear concept of appropriate message content. (C)Consultants would be able to avoid posting inappropriate messages on social networking if they have a good sense of self-awareness, and are able to reflect and assess the issue on hand. (D)Consultants need to pay attention to the content of messages on community websites as they have no control over the audiences’ interpretation of it. (E)Consultants should remain professional on social networking and this includes refraining from criticisms and inferences. Discoveries derived from analysis of the interview data: 1.Psychology consultants deem that social networking have become an interactive tool that is indispensable in both life and work 2.Psychology consultants’ value of individual privacy and are conscious of their input on social networking site. 3.Psychology consultants create an identity and role for themselves through the Internet and social networking 4.Psychology consultants are affected by their professional role and ethics responsibilities when using social networking sites. 5.Psychology consultants tend to be concerned over how individuals perceive the information they posted on social networking sites. 6.Psychology consultants believe that their messages on social networking may subconsciously affect the discussion on these sites. 7.Psychology consultants are influenced by their training in ethics and this makes them extra cautious when using social networking sites. 8.Psychology consultants tend to attempt to separate the “professional” and the “personal” on social networking sites. The following conclusion can be drawn from the above research and analysis of the results: 1.Recommendations for consultants (A)The importance of the effects of personal network-related messages on the consultant’s profession, work and case relationship (B)The intention usage, and function of social networking requires care and consideration. (C)In cases of ethical dilemma, consultants should seek advice and discussion with other professionals. 2.Recommendations for consultants’ training programs (A)Inclusion of Internet knowledge in training programs so consultants are familiar with its potential. (B)There should be a focus on the ethics training of consultants. 3.Recommendations for the future research (A)Public opinion on consultants’ usage of social networking sites. Consultants’ years of service can be included as a factor in the study.

Real-time social recommendation based on graph embedding and temporal context

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.

Nowadays, the issue of information overload is gradually gaining exposure in the Internet of Things (IoT), calling for more research on recommender system in advance for industrial IoT scenarios. With the ever-increasing prevalence of various social networks, social recommendations (SoR) will certainly become an integral application that provides more feasibly personalized information service for future IoT users. However, almost all of the existing research managed to explore and quantify correlations between user preferences and social relationships, while neglecting the correlations among item features which could further influence the topologies of some social groups. To tackle with this challenge, in this article, a deep graph neural network-based social recommendation framework (GNN-SoR) is proposed for future IoTs. First, user and item feature spaces are abstracted as two graph networks and respectively encoded via the graph neural network method. Next, two encoded spaces are embedded into two latent factors of matrix factorization to complete missing rating values in a user-item rating matrix. Finally, a large amount of experiments are conducted on three real-world data sets to verify the efficiency and stability of the proposed GNN-SoR.

When collecting information, local differential privacy (LDP) alleviates privacy concerns of users because their private information is randomized before being sent it to the central aggregator. LDP imposes large amount of noise as each user executes the randomization independently. To address this issue, recent work introduced an intermediate server with the assumption that this intermediate server does not collude with the aggregator. Under this assumption, less noise can be added to achieve the same privacy guarantee as LDP, thus improving utility for the data collection task. This paper investigates this multiple-party setting of LDP. We analyze the system model and identify potential adversaries. We then make two improvements: a new algorithm that achieves a better privacy-utility tradeoff; and a novel protocol that provides better protection against various attacks. Finally, we perform experiments to compare different methods and demonstrate the benefits of using our proposed method.

Local Differential Privacy (LDP) has been widely recognized as a powerful tool for providing a strong theoretical guarantee of data privacy to data contributors against an untrusted data collector. Under a typical LDP scheme, each data contributor independently randomly perturbs their data before submitting them to the data collector, which in turn infers valuable statistics about the original data from received perturbed data. Common to existing LDP mechanisms is an inherent trade-off between the level of privacy protection and data utility in the sense that strong data privacy often comes at the cost of reduced data utility. Frequency estimation based on Randomized Response (RR) is a fundamental building block of many LDP mechanisms. In this paper, we propose a novel Joint Randomized Response (JRR) mechanism based on correlated data perturbations to achieve locally differentially private frequency estimation. JRR divides data contributors into disjoint groups of two members and lets those in the same group jointly perturb their binary data to improve frequency-estimation accuracy and achieve the same level of data privacy by hiding the group membership information in contrast to the classical RR mechanism. Theoretical analysis and detailed simulation studies using both real and synthetic datasets show that JRR achieves the same level of data privacy as the classical RR mechanism while improving the frequency-estimation accuracy in the overwhelming majority of the cases by up to two orders of magnitude.