Saved in:
Bibliographic Details
Main Authors: Wang, Li, Sang, Lei, Zhang, Quangui, Wu, Qiang, Xu, Min
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.03600
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910355242876928
author Wang, Li
Sang, Lei
Zhang, Quangui
Wu, Qiang
Xu, Min
author_facet Wang, Li
Sang, Lei
Zhang, Quangui
Wu, Qiang
Xu, Min
contents Cross-domain recommendation (CDR) aims to enhance recommendation accuracy in a target domain with sparse data by leveraging rich information in a source domain, thereby addressing the data-sparsity problem. Some existing CDR methods highlight the advantages of extracting domain-common and domain-specific features to learn comprehensive user and item representations. However, these methods can't effectively disentangle these components as they often rely on simple user-item historical interaction information (such as ratings, clicks, and browsing), neglecting the rich multi-modal features. Additionally, they don't protect user-sensitive data from potential leakage during knowledge transfer between domains. To address these challenges, we propose a Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation, called P2M2-CDR. Specifically, we first design a multi-modal disentangled encoder that utilizes multi-modal information to disentangle more informative domain-common and domain-specific embeddings. Furthermore, we introduce a privacy-preserving decoder to mitigate user privacy leakage during knowledge transfer. Local differential privacy (LDP) is utilized to obfuscate the disentangled embeddings before inter-domain exchange, thereby enhancing privacy protection. To ensure both consistency and differentiation among these obfuscated disentangled embeddings, we incorporate contrastive learning-based domain-inter and domain-intra losses. Extensive Experiments conducted on four real-world datasets demonstrate that P2M2-CDR outperforms other state-of-the-art single-domain and cross-domain baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2403_03600
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation
Wang, Li
Sang, Lei
Zhang, Quangui
Wu, Qiang
Xu, Min
Artificial Intelligence
Cross-domain recommendation (CDR) aims to enhance recommendation accuracy in a target domain with sparse data by leveraging rich information in a source domain, thereby addressing the data-sparsity problem. Some existing CDR methods highlight the advantages of extracting domain-common and domain-specific features to learn comprehensive user and item representations. However, these methods can't effectively disentangle these components as they often rely on simple user-item historical interaction information (such as ratings, clicks, and browsing), neglecting the rich multi-modal features. Additionally, they don't protect user-sensitive data from potential leakage during knowledge transfer between domains. To address these challenges, we propose a Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation, called P2M2-CDR. Specifically, we first design a multi-modal disentangled encoder that utilizes multi-modal information to disentangle more informative domain-common and domain-specific embeddings. Furthermore, we introduce a privacy-preserving decoder to mitigate user privacy leakage during knowledge transfer. Local differential privacy (LDP) is utilized to obfuscate the disentangled embeddings before inter-domain exchange, thereby enhancing privacy protection. To ensure both consistency and differentiation among these obfuscated disentangled embeddings, we incorporate contrastive learning-based domain-inter and domain-intra losses. Extensive Experiments conducted on four real-world datasets demonstrate that P2M2-CDR outperforms other state-of-the-art single-domain and cross-domain baselines.
title A Privacy-Preserving Framework with Multi-Modal Data for Cross-Domain Recommendation
topic Artificial Intelligence
url https://arxiv.org/abs/2403.03600