DUPGT-CDR: Deep User Preference Gating Transfer for Cross-domain Recommendation

This repository is the official implementation of "DUPGT-CDR: Deep User Preference Gating Transfer for Cross-domain Recommendation," a manuscript currently being submitted to IEEE Access.

Related Work

CMF: Relational Learning via Collective Matrix Factorization Categories and Subject Descriptors (KDD 2008)

EMCDR: Cross-Domain Recommendation: An Embedding and Mapping Approach (IJCAI 2017)

PTUPCDR: Personalized Transfer of User Preferences for Cross-domain Recommendation (WSDM 2022)

DPTUPCDR: Tackling cold-start with deep personalized transfer of user preferences for cross-domain recommendation (Int J Data Sci Anal 20, 121–130 (2025))

MIMNet: Multi-interest Meta Network with Multi-granularity Target-guided Attention for cross-domain recommendation (Int J Neurocomputing vol. 620, p. 129208 (2025))

Dataset

We used the Movies & TV Shows, CDs & Records, and Books sections of the Amazon-5cores dataset for our experiments.Amazon Reviews Dataset.

Requirements

To run this project, you will need the following environment and packages:

• Python 3.6 or higher
• PyTorch 1.0 or higher
• TensorFlow
• Pandas
• NumPy
• Tqdm