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

Abstract

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

arXiv commentAccepted by TheWebConf'22 (WWW'22)

References in corpus (2)

• CoNet: Collaborative Cross Networks for Cross-Domain Recommendation
• CATN: Cross-Domain Recommendation for Cold-Start Users via Aspect Transfer Network

Cited by in corpus (9)

• Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey
• Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendation
• Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems
• Prompt-enhanced Federated Content Representation Learning for Cross-domain Recommendation
• Federated Learning on Non-iid Data via Local and Global Distillation
• In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems
• FedHCDR: Federated Cross-Domain Recommendation with Hypergraph Signal Decoupling
• BGTplanner: Maximizing Training Accuracy for Differentially Private Federated Recommenders via Strategic Privacy Budget Allocation
• Stalactite: Toolbox for Fast Prototyping of Vertical Federated Learning Systems