Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks

Liu, Meng; Li, Jianjun; Li, Guohui; Pan, Peng

doi:10.1145/3340531.3412012

Cited by 123 publications

(42 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, a user may like suspense novel and movie with different intension. Therefore it may be inappropriate to generate the common preference by manually summing over the domain-specific ones as does the existing method [13]. To address this issue, we propose a Multi-Domain Adaptation Network (MDAN) for DIAPE to learn a domain-invariant preference embedding matrix for each domain.…”

Section: Domain-invariant Aspect Preference Encoder (Diape)mentioning

confidence: 99%

“…• DDTCDR [11] DDTCDR is also a dual-target CDR model, which realizes the dual knowledge transfer between two domains, based on a cross-domain preference mapping with orthogonal constraints. • BiTGCF [13] BiTGCF is a GCN based dual-target CDR model, which can improve the recommendation performance of both domains simultaneously through a bidirectional knowledge transfer between the two domains.…”

Section: Model Trainingmentioning

confidence: 99%

“…The existing methods for dual-target CDR often apply bidirectional transfer learning to jointly model a user's preferences in two relevant domains [7,11,15,25,28]. Recently, researchers have also proposed a few graph-based methods for CDR, which apply GNN to capture the high-order relations between features of different domains [13,26,30]. PPGN [26] leverages GCN to capture the highorder information propagation over the joint user-item interaction graph across different domains.…”

Section: Related Workmentioning

confidence: 99%

“…GA-DTCDR [30] models the complex relations between users and items with a heterogeneous graph in each domain, and applies an element-wise graph attention network to fuse the embeddings of common users learned from both domains. BiTGCF [13] captures the high-order connectivity in useritem graph of single domain through GCN, and realizes a two-way transfer between two domains with the common user as anchors.…”

Section: Related Workmentioning

confidence: 99%

See 3 more Smart Citations

Multi-Sparse-Domain Collaborative Recommendation via Enhanced Comprehensive Aspect Preference Learning

Zhao

Yang

2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Cross-domain recommendation (CDR) has been attracting increasing attention of researchers for its ability to alleviate the data sparsity problem in recommender systems. However, the existing singletarget or dual-target CDR methods often suffer from two drawbacks, the assumption of at least one rich domain and the heavy dependence on domain-invariant preference, which are impractical in real world where sparsity is ubiquitous and might degrade the user preference learning. To overcome these issues, we propose a Multi-Sparse-Domain Collaborative Recommendation (MSDCR) model for multi-target cross-domain recommendation. Unlike traditional CDR methods, MSDCR treats the multiple relevant domains as all sparse and can simultaneously improve the recommendation performance in each domain. We propose a Multi-Domain Separation Network (MDSN) and a Gated Aspect Preference Enhancement (GAPE) module for MSDCR to enhance a user's domain-specific aspect preferences in a domain by transferring the complementary aspect preferences in other domains, during which the uniqueness of the domain-specific preference can be preserved through the adversarial training offered by MDSN and the complementarity can be adaptively determined by GAPE. Meanwhile, we propose a Multi-Domain Adaptation Network (MDAN) for MSDCR to capture a user's domain-invariant aspect preference. With the integration of the enhanced domain-specific aspect preference and the domaininvariant aspect preference, MSDCR can reach a comprehensive understanding of a user's preference in each sparse domain. At last, the extensive experiments conducted on real datasets demonstrate the remarkable superiority of MSDCR over the state-of-the-art single-domain recommendation models and CDR models. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Section: Domain-invariant Aspect Preference Encoder (Diape)mentioning

confidence: 99%

Section: Model Trainingmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Multi-Sparse-Domain Collaborative Recommendation via Enhanced Comprehensive Aspect Preference Learning

Zhao

Yang

2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

“…The cross-domain recommendation (CDR) has been studied [13]- [20] to solve the cold-start problem. CDR is a VOLUME x, 2019 FIGURE 1.…”

Section: Introductionmentioning

confidence: 99%

Refining Graph Representation for Cross-Domain Recommendation Based on Edge Pruning in Latent Space

et al. 2022

View full text Add to dashboard Cite

In this paper, we present refining graph representation for cross-domain recommendation (CDR) based on edge pruning considering feature distribution in a latent space. Conventional graph-based CDR methods have utilized all ratings and purchase histories of user's products. However, some items purchased by users are not related to the domain for recommendation, and this information becomes noise when making CDR. So, the proposed method introduces edge pruning into the latest graph-based CDR method to refine graph representation. To compare the item embedding features calculated in different domains, we construct a latent space and perform edge pruning through their correlations. Additionally, we introduce a state-of-the-art graph neural network into the graph construction of the proposed method that considers the interactions between users and items thereby obtaining effective embedding features in a domain. This makes it possible to consider domain-specific user preferences and estimate embedding features with high-expressive power. Furthermore, to compare the embedding features of items in the two domains, we construct their latent spaces and project them. Edge pruning is performed using the correlation of items between the two domains on the latent space. We obtain cross domain specific graph representation through edge pruning, which improves the performance by considering the relationship between both items across domains. To the best of our knowledge, no study in the CDR field focuses on eliminating unnecessary node information. We have demonstrated the effectiveness of the proposed method by comparing several graph-based state-of-the-art methods.INDEX TERMS Edge pruning, cross-domain recommendation, latent space graph convolutional networks.

show abstract

Attention-Based Multi-view Feature Fusion for Cross-Domain Recommendation

Dai

Wang³

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Cross Domain Recommendation via Bi-directional Transfer Graph Collaborative Filtering Networks

Cited by 123 publications

References 31 publications

Multi-Sparse-Domain Collaborative Recommendation via Enhanced Comprehensive Aspect Preference Learning

Multi-Sparse-Domain Collaborative Recommendation via Enhanced Comprehensive Aspect Preference Learning

Refining Graph Representation for Cross-Domain Recommendation Based on Edge Pruning in Latent Space

Attention-Based Multi-view Feature Fusion for Cross-Domain Recommendation

Contact Info

Product

Resources

About