A two-stage locality-sensitive hashing based approach for privacy-preserving mobile service recommendation in cross-platform edge environment

摘要: Abstract With the increasing popularity of service computing paradigm, tremendous resources or services are emerging rapidly on Web, imposing heavy burdens selection decisions users. In this situation, recommendation (e.g., collaborative filtering) has been considered as one most effective ways to alleviate such burdens. However, in mobile and edge environment, bases, i.e., historical usage data often generated from various devices Smartphone PDA) stored different platforms. Therefore, collaboration between these distributed platforms plays an important role successful recommendation. Such a cross-platform process faces following two challenges. First, platform is reluctant release its other due privacy concerns. Second, efficiency low when each update frequently. view challenges, we introduce MinHash, instance Locality-Sensitive Hashing (LSH), into recommendation, further put forward novel privacy-preserving scalable approach based two-stage LSH, named SerRec t w o - L S H . Finally, extensive experiments conducted WS-DREAM, real quality dataset, evaluation results demonstrate that both accuracy scalability have significantly improved while preservation guaranteed.