Toward Equivalent Transformation of User Preferences in Cross Domain Recommendation

Chen, Xu; Zhang, Ya; Tsang, Ivor W.; Pan, Yuangang; Su, Jingchao

doi:10.1145/3522762

Cited by 17 publications

(3 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While DDTCDR does not have optimization for refining feature fusion, so the performance is relatively poor. The performance of Conet is not satisfactory, and there are similar results in (Chen et al 2020), because its learning mechanism breaks the joint behavior pattern in CDR. P2FCDR performs even better than those crossdomain methods with the risk of leaking user privacy.…”

Section: Performance Evaluationmentioning

confidence: 96%

“…Datasets We study the effectiveness of our P2FCDR on three largest domains on a real-world public dataset Amazon 1 , i.e., Movies and TV (Movie), Books (Book), and CD Vinyl (Music). Following (Chen et al 2020(Chen et al , 2022, we make a pairwise combinations amongst the three domains and only choose the user-item interactions of the common users across domains, i.e., Movie & Book, Music & Movie, and Book & Music. For the data in these three couple datasets, we first transform them into implicit data, where each entry is marked as 0 or 1, indicating whether the user has rated the item.…”

Section: Experiments Experimental Setupmentioning

confidence: 99%

See 1 more Smart Citation

Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation

Chen

Zhang

et al. 2023

AAAI

View full text Add to dashboard Cite

Cross-domain recommendation (CDR) aims to alleviate the data sparsity by transferring knowledge from an informative source domain to the target domain, which inevitably proposes stern challenges to data privacy and transferability during the transfer process. A small amount of recent CDR works have investigated privacy protection, while they still suffer from satisfying practical requirements (e.g., limited privacy-preserving ability) and preventing the potential risk of negative transfer. To address the above challenging problems, we propose a novel and unified privacy-preserving federated framework for dual-target CDR, namely P2FCDR. We design P2FCDR as peer-to-peer federated network architecture to ensure the local data storage and privacy protection of business partners. Specifically, for the special knowledge transfer process in CDR under federated settings, we initialize an optimizable orthogonal mapping matrix to learn the embedding transformation across domains and adopt the local differential privacy technique on the transformed embedding before exchanging across domains, which provides more reliable privacy protection. Furthermore, we exploit the similarity between in-domain and cross-domain embedding, and develop a gated selecting vector to refine the information fusion for more accurate dual transfer. Extensive experiments on three real-world datasets demonstrate that P2FCDR significantly outperforms the state-of-the-art methods and effectively protects data privacy.

show abstract

Section: Performance Evaluationmentioning

confidence: 96%

Section: Experiments Experimental Setupmentioning

confidence: 99%

Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation

Chen

Zhang

et al. 2023

AAAI

View full text Add to dashboard Cite

show abstract

“…Cross-domain recommendations with single source domain, such as cross-domain triadic factorization (CDTF) [41], deep domain adaptation model (DARec) [42] , and equivalent transformation learner (ETL) [43] were proposed to transfer user-item preference relations from a single source domain to a target domain without relying on any auxiliary information. By combining content information, a transfer meeting contentaware method (TMH) [44] is formulated with unstructured text in an end-to-end manner.…”

Section: B Cross-domain Recommender Systemsmentioning

confidence: 99%

Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations

Zhang¹,

Li²,

Tsang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Cold-start issues have been more and more challenging for providing accurate recommendations with the fast increase of users and items. Most existing approaches attempt to solve the intractable problems via content-aware recommendations based on auxiliary information and/or cross-domain recommendations with transfer learning. Their performances are often constrained by the extremely sparse user-item interactions, unavailable side information, or very limited domain-shared users. Recently, meta-learners with meta-augmentation by adding noises to labels have been proven to be effective to avoid overfitting and shown good performance on new tasks. Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a socalled Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues. Specifically, we first conduct multi-source domain adaptation by dual conditional variational autoencoders and impose a Multidomain InfoMax (MDI) constraint on the latent representations to learn domain-shared and domain-specific preference properties. To avoid overfitting, we add a Mutually-Exclusive (ME) constraint on the output of decoders to generate diverse ratings given content data. Finally, these generated diverse ratings and the original ratings are introduced into the meta-training procedure to learn a preference meta-learner, which produces good generalization ability on cold-start recommendation tasks. Experiments on real-world datasets show our proposed MetaDPA clearly outperforms the current state-of-the-art baselines.

show abstract

Enhancing user experience: a content-based recommendation approach for addressing cold start in music recommendation

Jangid,

Kumar

2024

J Intell Inf Syst

View full text Add to dashboard Cite

Toward Equivalent Transformation of User Preferences in Cross Domain Recommendation

Cited by 17 publications

References 61 publications

Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation

Win-Win: A Privacy-Preserving Federated Framework for Dual-Target Cross-Domain Recommendation

Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations

Enhancing user experience: a content-based recommendation approach for addressing cold start in music recommendation

Contact Info

Product

Resources

About