From Personalization to Privatization: Meta Matrix Factorization for Private Rating Predictions

Matrix factorization (MF) techniques have been shown to be effective for rating predictions (RPs) in personalized recommender systems. Existing MF methods use the same item embeddings and the same RP model for all users, while ignoring the possibility that different users may have different views about the same item and may favor different RP models. We introduce a novel MF framework, named meta matrix factorization (MetaMF), that generates private item embeddings and RP models. Given a vector representing a user, we first obtain a collaborative vector by collecting useful information from all users with a collaborative memory (CM) module. Then, we employ a meta recommender (MR) module to generate private item embeddings and a RP model based on the collaborative vector. To address the challenge of generating a large number of high-dimensional item embeddings, we devise a rise-dimensional generation (RG) strategy that first generates a low-dimensional item embedding matrix and a rise-dimensional matrix, and then multiply them to obtain high-dimensional embeddings. Finally, we use the generated model to produce private RPs for a given user. Experiments on two benchmark datasets show that MetaMF outperforms state-of-the-art MF methods. MetaMF generates similar/dissimilar item embeddings and models for different users to flexibly exploit collaborative filtering (CF), demonstrating the benefits of MetaMF.