Combining Graph Contrastive Embedding and Multi-head Cross-Attention Transfer for Cross-Domain Recommendation

• Published in: Data Science and Engineering Vol. 8; no. 3; pp. 247 - 262
• Main Authors: Xiao, Shuo, Zhu, Dongqing, Tang, Chaogang, Huang, Zhenzhen
• Format: Journal Article
• Language: English
• Published: Singapore Springer Nature Singapore 01.09.2023; Springer; Springer Nature B.V; SpringerOpen
• Subjects: Algorithm Analysis and Problem Complexity; Artificial Intelligence; Bias; Chemistry and Earth Sciences; Computer Science; Contrastive learning; Cross-domain recommendation; Data Mining and Knowledge Discovery; Database Management; Deep learning; Embedding; Knowledge management; Long-tail distribution; Motion picture directors & producers; Multi-head cross-attention; Physics; Popularity; Recommender systems; Research Paper; Sparsity; Statistics for Engineering; Systems and Data Security; Cross-domain recommendation; Long-tail distribution; Multi-head cross-attention; Contrastive learning
• DOI: 10.1007/s41019-023-00226-7
• ISSN: 2364-1185

Cross-domain recommendation (CDR) has become an important research direction in the field of recommender systems due to the increasing demand for personalized recommendations across different domains. However, CDR faces multiple challenges, including data sparsity, popularity bias, and long-tail problems. To address these challenges, we propose a novel framework that combines graph contrastive embedding and multi-head cross-attention transfer for cross-domain recommendation, called GCE-MCAT. Specifically, in the pre-training process, we generate more uniform user and item embeddings through contrastive learning, effectively solving the problem of inconsistent data embedding space distribution and recommendation popularity bias. Moreover, we propose a multi-head cross-attention transfer mechanism that allows the model to extract user common and specific domain features from multiple perspectives and perform cross-domain bidirectional knowledge transfer. Finally, we propose a cross-domain feature fusion mechanism that dynamically assigns weights to common user features and specific domain features. This enables the model to more effectively learn common user interests. We evaluate the proposed framework on three real-world CDR datasets and show that GCE-MCAT consistently and significantly improves recommendation performance compared to state-of-the-art methods. In particular, the proposed framework has demonstrated remarkable effectiveness in addressing long-tail distribution and enhancing recommendation novelty, providing users with more diversified recommendations and reducing popularity bias.