DDTCDR: Deep Dual Transfer Cross Domain Recommendation

2019/10/11 by Li Pan, Pan Li, Li, Pan +2 · 36 citations
Computer Science · Mathematics · #Advanced Graph Neural Networks #Artificial intelligence #Autoencoder #Computer science #Deep learning #Domain (mathematical analysis) #Dual (grammatical number) #FOS: Computer and information sciences #Feature (linguistics) #Information Retrieval (cs.IR) #Information retrieval #Machine Learning (cs.LG) #Machine learning #Mathematics #Process (computing) #Recommender Systems and Techniques #Recommender system #Topic Modeling #Transfer of learning #cs.IR #cs.LG

paper · pdf · doi:10.48550/arxiv.1910.05189

published in arXiv (Cornell University) (Cornell University) · Accepted to WSDM 2020

arxiv created 2019/10/11 · openalex publication_date 2019/10/11 · arxiv updated 2019/10/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08

Abstract

Cross domain recommender systems have been increasingly valuable for helping consumers identify the most satisfying items from different categories. However, previously proposed cross-domain models did not take into account bidirectional latent relations between users and items. In addition, they do not explicitly model information of user and item features, while utilizing only user ratings information for recommendations. To address these concerns, in this paper we propose a novel approach to cross-domain recommendations based on the mechanism of dual learning that transfers information between two related domains in an iterative manner until the learning process stabilizes. We develop a novel latent orthogonal mapping to extract user preferences over multiple domains while preserving relations between users across different latent spaces. Combining with autoencoder approach to extract the latent essence of feature information, we propose Deep Dual Transfer Cross Domain Recommendation (DDTCDR) model to provide recommendations in respective domains. We test the proposed method on a large dataset containing three domains of movies, book and music items and demonstrate that it consistently and significantly outperforms several state-of-the-art baselines and also classical transfer learning approaches.

Citations

• Auto-Encoding Variational Bayes
• Matrix Factorization Techniques for Recommender Systems
• Sequence to Sequence Learning with Neural Networks
• A Survey on Transfer Learning

Cited by

• Meta Lattice: Model Space Redesign for Cost-Effective Industry-Scale Ads Recommendations
• LLM-EDT: Large Language Model Enhanced Cross-domain Sequential Recommendation with Dual-phase Training
• Causality Enhancement for Cross-Domain Recommendation
• Hierarchical Semantic RL: Tackling the Problem of Dynamic Action Space for RL-based Recommendations
• Modeling User Preferences as Distributions for Optimal Transport-based Cross-domain Recommendation under Non-overlapping Settings
• Dual prototype attentive graph network for cross-market recommendation
• Generative Multi-Target Cross-Domain Recommendation
• GIST: Cross-Domain Click-Through Rate Prediction via Guided Content-Behavior Distillation
• Empowering Cross-Domain Sequential Recommendation with Hybrid Tokenization and Serial-Parallel Decoding
• LLM-Enhanced Multimodal Fusion for Cross-Domain Sequential Recommendation
• Semantic-enhanced Co-attention Prompt Learning for Non-overlapping Cross-Domain Recommendation
• FedGRec: Dynamic Spatio-Temporal Federated Graph Learning for Secure and Efficient Cross-Border Recommendations
• Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations

Related

• Dual Metric Learning for Effective and Efficient Cross-Domain Recommendations
• A cross-domain recommender system using deep coupled autoencoders
• Towards Equivalent Transformation of User Preferences in Cross Domain Recommendation
• A Unified Framework for Adaptive Representation Enhancement and Inversed Learning in Cross-Domain Recommendation
• A Survey on Cross-domain Recommendation: Taxonomies, Methods, and Future Directions