Amplified locality-sensitive hashing for privacy-preserving distributed service recommendation

With the ever-increasing volume of services registered in various web communities, service recommendation techniques, e.g., Collaborative Filtering (i.e., CF) have provided a promising way to alleviate the heavy burden on the service selection decisions of target users. However, traditional CF-based service recommendation approaches often assume that the recommendation bases, i.e., historical service quality data are centralized, without considering the distributed service recommendation scenarios as well as the resulted privacy leakage risks. In view of this shortcoming, Locality-Sensitive Hashing (LSH) technique is recruited in this paper to protect the private information of users when distributed service recommendations are made. Furthermore, LSH is essentially a probability-based search technique and hence may generate “False-positive” or “False-negative” recommended results; therefore, we amplify LSH by AND/OR operations to improve the recommendation accuracy. Finally, through a set of experiments deployed on a real distributed service quality dataset, i.e., WS-DREAM, we validate the feasibility of our proposed recommendation approach named DistSR Amplify-LSH in terms of recommendation accuracy and efficiency while guaranteeing privacy-preservation in the distributed environment.