Community-based social recommendation under local differential privacy protection

Abstract

Social recommendation refers to recommendation technology taking social relations as additional input to improve merchandise sales and user satisfaction. It has been widely used in various social networking services. Social recommendation requires the collection of each user's social relations to build a social graph, posing the risk of user privacy intrusion caused by untrusted servers. Local differential privacy is a widely adopted approach for providing privacy protection while allowing acceptable utility of the protected data for analytics. Growing research interest has been applying local differential privacy protection to social graph analysis. However, local differential privacy is suitable for analyzing coarse-grained statistics from perturbed user data, and it is difficult to obtain the fine-grained user relations needed for social recommendation. This paper proposes a novel locally differentially private social recommendation method. It first perturbs the degrees of users in a given interval and discovers coarse-grained communities from them, then generates a fine-grained social graph according to the features of intra-community and inter-community relations, thus ensuring the accuracy of the recommendation results. Experimental results show that the social recommendation accuracy of our proposed method improves by about 20% compared to existing methods in a community-structured ego-network dataset, and by about 10% in two non-community-structured page-page network datasets. The experimental results show that compared with the state-of-the-art methods such as LDPGen, LFGDPR, and AsgLDP, the social recommendation accuracy of our proposed method is improved by about 20% in one community-structured ego-network dataset, and 10% in two non-community-structured page-page network datasets.