Federated CF: Privacy-Preserving Collaborative Filtering Cross Multiple Datasets
Le Wang, Zijun Huang, Qingqi Pei, Shen Wang · 2020
In the era of information exploration, collaborative filtering algorithms have been widely adopted to offer useful contents according the different preferences of the users. Unfortunately, due to the sparsity of the original rating data, different data owners are highly motivated to collaborate with each other to guarantee the prediction accuracy via CF algorithms. However, as the original rating data contains sensitive information of the users, strict privacy preserving requirements might hinder the collaboration of different data owners. Although there exist some works to address the privacy issues in CF, they do not consider the cases where the CF algorithms are executed based the integration of multiple datasets. Thus in this paper, we propose a privacy-preserving multiparty scheme for collaborative filtering, using mixed MPC protocols combined with Yao garbled circuit and additive secret sharing. And the accuracy and efficiency of the proposed scheme is verified under the real dataset.