A Unified Framework for Cross-Domain and Cross-System Recommendations

Zhu, Feng; Wang, Yan; Zhou, Jùn; Chen, Chaochao; Li, Longfei; Liu, Guanfeng

doi:10.1109/tkde.2021.3104873

Cited by 45 publications

(15 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The Amazon dataset [26,33] has three domains, i.e., Movies and TV (Movie), Books (Book), and CD Vinyl (Music). The Douban dataset [34,36] also has three domains, i.e., Book, Music, and Movie. Since the user-item interaction ratings in both datasets range from 0 to 5, we binarize them by taking the ratings that are higher or equal to 3 as positive and others as negative, following [17].…”

Section: Methodsmentioning

confidence: 99%

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

Chen,

Wu,

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

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 this problem, 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) and Sparse-aware JLT (SJLT), to publish the rating matrix of the source domain using Differential Privacy (DP). We theoretically analyze the privacy and utility of our proposed DP 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 PriCDR and HeteroCDR. CCS CONCEPTS• Security and privacy → Privacy protections; • Computing methodologies → Machine learning.

show abstract

Section: Methodsmentioning

confidence: 99%

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

Chen,

Wu,

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…On the one hand, researchers extensively incorporate other kinds of information, e.g., social [27], review [25], location [16], and time [7], to further improve recommendation performance. On the other hand, existing studies begin to explore information on multiple platforms or domains to address the data sparsity problem in recommender systems, i.e., cross-platform and cross-domain recommendation [17,34,33]. However, most of them cannot solve the data isolation problem in practice.…”

Section: Related Workmentioning

confidence: 99%

Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation

Cui¹,

Chen²,

Lyu

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Social recommendation has shown promising improvements over traditional systems since it leverages social correlation data as an additional input. Most existing works assume that all data are available to the recommendation platform. However, in practice, user-item interaction data (e.g., rating) and user-user social data are usually generated by different platforms, both of which contain sensitive information. Therefore, How to perform secure and efficient social recommendation across different platforms, where the data are highly-sparse in nature remains an important challenge. In this work, we bring secure computation techniques into social recommendation, and propose S 3 Rec, a sparsity-aware secure cross-platform social recommendation framework. As a result, S 3 Rec can not only improve the recommendation performance of the rating platform by incorporating the sparse social data on the social platform, but also protect data privacy of both platforms. Moreover, to further improve model training efficiency, we propose two secure sparse matrix multiplication protocols based on homomorphic encryption and private information retrieval. Our experiments on two benchmark datasets demonstrate that S 3 Rec improves the computation time and communication size of the state-of-the-art model by about 40× and 423× in average, respectively.

show abstract

“…We conduct extensive experiments on two popularly used realworld datasets, i.e., Douban and Amazon. First, the Douban dataset [53,55] has three domains, i.e., Book, Music, and Movie. Second, the Amazon dataset [31,51] has five domains, i.e., Movies and TV (Movie), Books (Book), CDs and Vinyl (Music), Instant Videos (Video) and Clothes (Clothes).…”

Section: Datasets and Tasksmentioning

confidence: 99%

Collaborative Filtering with Attribution Alignment for Review-based Non-overlapped Cross Domain Recommendation

Liu¹,

Zheng²,

Hu³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Cross-Domain Recommendation (CDR) has been popularly studied to utilize different domain knowledge to solve the data sparsity and cold-start problem in recommender systems. In this paper, we focus on the Review-based Non-overlapped Recommendation (RNCDR) problem. The problem is commonly-existed and challenging due to two main aspects, i.e, there are only positive user-item ratings on the target domain and there is no overlapped user across different domains. Most previous CDR approaches cannot solve the RNCDR problem well, since (1) they cannot effectively combine review with other information (e.g., ID or ratings) to obtain expressive user or item embedding, (2) they cannot reduce the domain discrepancy on users and items. To fill this gap, we propose Collaborative Filtering with Attribution Alignment model (CFAA), a cross-domain recommendation framework for the RNCDR problem. CFAA includes two main modules, i.e., rating prediction module and embedding attribution alignment module. The former aims to jointly mine review, one-hot ID, and multi-hot historical ratings to generate expressive user and item embeddings. The later includes vertical attribution alignment and horizontal attribution alignment, tending to reduce the discrepancy based on multiple perspectives. Our empirical study on Douban and Amazon datasets demonstrates that CFAA significantly outperforms the state-of-the-art models under the RNCDR setting.

show abstract

A Unified Framework for Cross-Domain and Cross-System Recommendations

Cited by 45 publications

References 62 publications

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

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

Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation

Collaborative Filtering with Attribution Alignment for Review-based Non-overlapped Cross Domain Recommendation

Contact Info

Product

Resources

About