A Comprehensive Survey on Cross-Domain Recommendation: Taxonomy, Progress, and Prospects

TL;DR

The paper provides a technical overview of Cross-Domain Recommendation (CDR), framing it around a three-stage workflow: establishing inter-domain connections, modeling cross-domain interactions, and delivering cross-domain recommendations. It offers a taxonomy centered on cross-domain relevance, interaction, representation enhancement, and model optimization, and surveys advances in graph-based and attention-based integration, contrastive and disentangled representation learning, and LLM/multimodal approaches. Key contributions include organizing a wide range of methods (from DA-GCN and knowledge-graph models to UniCDR/UniSRec and MoEs) and highlighting practical applications, datasets, and resources. The work also articulates challenges such as negative transfer and privacy, and outlines future directions including large-language-model integration, lifelong and multimodal learning, and universal recommender systems, to guide both research and industry adoption.

Abstract

Recommender systems (RS) have become crucial tools for information filtering in various real world scenarios. And cross domain recommendation (CDR) has been widely explored in recent years in order to provide better recommendation results in the target domain with the help of other domains. The CDR technology has developed rapidly, yet there is a lack of a comprehensive survey summarizing recent works. Therefore, in this paper, we will summarize the progress and prospects based on the main procedure of CDR, including Cross Domain Relevance, Cross Domain Interaction, Cross Domain Representation Enhancement and Model Optimization. To help researchers better understand and engage in this field, we also organize the applications and resources, and highlight several current important challenges and future directions of CDR. More details of the survey articles are available at https://github.com/USTCAGI/Awesome-Cross-Domain Recommendation-Papers-and-Resources.

Figures (2)

• Figure 1: The procedures of cross domain recommender system.
• Figure 2: Summary of Cross Domain Recommendation methods.