Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation

Abstract

Social recommendation has shown promising improvements over traditional systems since it leverages social correlation data as an additional input. Most existing works assume that all data are available to the recommendation platform. However, in practice, user-item interaction data (e.g., rating) and user-user social data are usually generated by different platforms, both of which contain sensitive information. Therefore, How to perform secure and efficient social recommendation across different platforms, where the data are highly-sparse in nature remains an important challenge. In this work, we bring secure computation techniques into social recommendation, and propose S 3 Rec, a sparsity-aware secure cross-platform social recommendation framework. As a result, S 3 Rec can not only improve the recommendation performance of the rating platform by incorporating the sparse social data on the social platform, but also protect data privacy of both platforms. Moreover, to further improve model training efficiency, we propose two secure sparse matrix multiplication protocols based on homomorphic encryption and private information retrieval. Our experiments on two benchmark datasets demonstrate that S 3 Rec improves the computation time and communication size of the state-of-the-art model by about 40× and 423× in average, respectively.

Enhancing e-commerce recommendation systems through approach of buyer's self-construal: necessity, theoretical ground, synthesis of a six-step model, and research agenda

“…In a cross-platform recommendation system, where the future of recommendation systems is going to be, privacy is a problem because not only does each company need to decide how to keep their data private, but they also need to decide how and what to share with other platforms. The solution has been researched by authors such as Qi et al ( 2018 ) and Cui et al ( 2021 ). The common approaches to achieve this goal are pseudonymization and anonymization of consumers' data (the formal approach is where companies encrypt consumers' personal information in their database, and the latter approach is where the data collection was conducted in a way that the consumer is not identifiable) (Hintze and El Emam, 2016 ).…”