Differential Private Knowledge Transfer for Privacy-Preserving Cross-Domain Recommendation

• DOI: 10.1145/3485447.3512192
• Publication Date: 2022-04-25T05:11:23Z
• Authors: Chaochao Chen; Huiwen Wu; Jiajie Su; Lingjuan Lyu; Xiaolin Zheng; Li Wang
• Keywords: Differential Privacy; Knowledge Transfer

Cross Domain Recommendation (CDR) has been popularly studied to alleviate the cold-start and data sparsity problem commonly existed in recommender systems. CDR models can improve recommendation performance of a target domain by leveraging other source domains. However, most existing assume information directly 'transfer across bridge', ignoring privacy issues. To solve concern CDR, this paper, we propose novel two stage based privacy-preserving framework (PriCDR). In first stage, methods, i.e., Johnson-Lindenstrauss Transform (JLT) Sparse-awareJLT (SJLT) based, publish rating matrix using differential privacy. We theoretically analyze utility our proposed publishing methods. second heterogeneous model (HeteroCDR), which uses deep auto-encoder neural network published respectively. end, PriCDR not only protect domain, but also domain. conduct experiments on benchmark datasets results demonstrate effectiveness HeteroCDR.