A Comprehensive Survey on Cross-Domain Recommendation: Taxonomy, Progress, and Prospects
Overview
| Field | Detail | |-------|--------| | Title | A Comprehensive Survey on Cross-Domain Recommendation: Taxonomy, Progress, and Prospects | | Authors | Hao Zhang, Mingyue Cheng, Qi Liu, Junzhe Jiang, Xianquan Wang, Rujiao Zhang, et al. (8 authors) | | Published | 2025-03-18 | | Link | https://arxiv.org/abs/2503.14110 | | Type | Survey | | Resources | https://github.com/USTCAGI/Awesome-Cross-Domain-Recommendation-Papers-and-Resources |
Original 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.
Background and Motivation
Large-scale search, recommendation, and personalization systems have long faced challenges in efficiency, scalability, and user intent understanding. Traditional pipelines often treat retrieval, ranking, and generation as disconnected stages, which struggles to meet the demands of the LLM era: natural language interaction, multi-hop reasoning, and real-time knowledge. This survey systematically organizes the theory and practice of cross-domain recommendation (CDR) — using knowledge from other domains to improve recommendations in a target domain — at a time when CDR technology is developing rapidly but lacks a comprehensive, up-to-date survey.
Survey Taxonomy
The survey organizes CDR research along the main procedural stages:
1. Cross Domain Relevance — identifying relatedness between domains; 2. Cross Domain Interaction — mechanisms for transferring information across domains; 3. Cross Domain Representation Enhancement — improving shared/user/item representations; 4. Model Optimization — training strategies for cross-domain transfer.
A broader methodological view contrasts:
| Dimension | Subclasses | Representative ideas | Strengths | Limitations | |-----------|-----------|---------------------|-----------|-------------| | Modeling paradigm | Discriminative vs. generative retrieval | Two-tower, cross-encoder, DSI | Mature, scalable | Semantic drift, update cost | | LLM integration | RAG / Agent / Tool-use | Retrieval augmentation, search agents, API calls | Flexible, interpretable | Latency, error propagation | | Optimization goals | Relevance / diversity / freshness | Multi-objective LTR, RLHF, online learning | Business-aligned | Scarce labels | | Evaluation | Offline / Online / Human | nDCG, MRR, LLM-as-judge, A/B tests | Comparable | Deviates from real satisfaction |
Research Evolution
- 2019–2021: BERT-based re-ranking and DPR establish neural retrieval foundations;
- 2022–2023: RAG and retrieval-generation fusion gain momentum;
- 2024: Conversational/agentic search and generative recommender systems (Gen-RecSys) flourish;
- 2025–2026: RL-trained search agents, Deep Research, and GraphRAG emerge as growth areas.
- Lack of unified benchmarks and reproducible private data;
- LLM evaluation bias;
- Safety and cost constraints for agentic systems;
- Finer-grained process supervision, retrieval-reasoning co-training, multimodal and cross-lingual consistency.
- A Comprehensive Survey on Retrieval Methods in Recommender Systems
- A Survey of Generative Search and Recommendation in the Era of Large Language Models
- A Survey on LLM-powered Agents for Recommender Systems
- A Comprehensive Review on Harnessing Large Language Models
Key Takeaways
1. Architecture: cascaded retrieval + re-ranking + generation remains mainstream, but agentic paradigms make retrieval strategy itself learnable; 2. Data: high-quality instruction data and click/session logs are critical; synthetic data must guard against leakage and distribution shift; 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human assessment; 4. Productization: latency, cost, explainability, and safety are hard industrial constraints.
Open Problems and Future Directions
Related Entries
Glossary
| Term | Meaning | |------|---------| | IR | Information Retrieval | | RAG | Retrieval-Augmented Generation | | LTR | Learning to Rank | | nDCG | Normalized Discounted Cumulative Gain | | Agentic Search | Search modeled as sequential decision-making and tool use | | Gen-IR | Generative Information Retrieval |