A privacy-preserving framework with multi-modal data for cross-domain recommendation

Wang, L; Sang, L; Zhang, Q; Wu, Q; Xu, M

A privacy-preserving framework with multi-modal data for cross-domain recommendation

Wang, L Sang, L Zhang, Q Wu, Q Xu, M

Permalink

Publisher:: ELSEVIER
Publication Type:: Journal Article
Citation:: Knowledge-Based Systems, 2024, 304
Issue Date:: 2024-11-25

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (1.41 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Wang, L
dc.contributor.author	Sang, L
dc.contributor.author	Zhang, Q
dc.contributor.author	Wu, Q
dc.contributor.author	Xu, M https://orcid.org/0000-0001-9581-8849
dc.date.accessioned	2025-01-19T21:32:25Z
dc.date.available	2025-01-19T21:32:25Z
dc.date.issued	2024-11-25
dc.identifier.citation	Knowledge-Based Systems, 2024, 304
dc.identifier.issn	0950-7051
dc.identifier.issn	1872-7409
dc.identifier.uri	http://hdl.handle.net/10453/183825
dc.description.abstract	Cross-domain recommendation (CDR) aims to enhance the 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 cannot 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. In addition, they do not 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 used to obfuscate disentangled embeddings before the 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 six CDR tasks from two real-world datasets demonstrate that P2M2-CDR outperforms other state-of-the-art single- and cross-domain baselines. The code is available at https://github.com/Lili1013/P2M2-CDR.
dc.language	English
dc.publisher	ELSEVIER
dc.relation	http://purl.org/au-research/grants/arc/LP210100129
dc.relation.ispartof	Knowledge-Based Systems
dc.relation.isbasedon	10.1016/j.knosys.2024.112529
dc.rights	info:eu-repo/semantics/openAccess
dc.subject	08 Information and Computing Sciences, 15 Commerce, Management, Tourism and Services, 17 Psychology and Cognitive Sciences
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	4602 Artificial intelligence
dc.subject.classification	4605 Data management and data science
dc.subject.classification	4611 Machine learning
dc.title	A privacy-preserving framework with multi-modal data for cross-domain recommendation
dc.type	Journal Article
utslib.citation.volume	304
utslib.for	08 Information and Computing Sciences
utslib.for	15 Commerce, Management, Tourism and Services
utslib.for	17 Psychology and Cognitive Sciences
pubs.organisational-group	University of Technology Sydney
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
pubs.organisational-group	University of Technology Sydney/UTS Groups
pubs.organisational-group	University of Technology Sydney/UTS Groups/Global Big Data Technologies Centre (GBDTC)
utslib.copyright.status	open_access	*
dc.rights.license	This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0). To view a copy of this license, visit https://creativecommons.org/licenses/by/4.0/
dc.date.updated	2025-01-19T21:32:23Z
pubs.publication-status	Published
pubs.volume	304

Abstract:

Cross-domain recommendation (CDR) aims to enhance the 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 cannot 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. In addition, they do not 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 used to obfuscate disentangled embeddings before the 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 six CDR tasks from two real-world datasets demonstrate that P2M2-CDR outperforms other state-of-the-art single- and cross-domain baselines. The code is available at https://github.com/Lili1013/P2M2-CDR.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/183825