# Contrastive Graph Prompt-tuning for Cross-domain Recommendation

arXiv: https://arxiv.org/abs/2308.10685 · HTML: https://mlsanity.com/paper/2308.10685/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Aug 2023.

## Built on by (most cited first, 9 of 9)

- [Graph Prompt Learning: A Comprehensive Survey and Beyond](https://mlsanity.com/paper/2311.16534/) (2023)
- [Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphs](https://mlsanity.com/paper/2311.15317/) (2023)
- [SPELL: Semantic Prompt Evolution based on a LLM](https://mlsanity.com/paper/2310.01260/) (2023)
- [GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning](https://mlsanity.com/paper/2511.05592/) (2025)
- [Exploring Prompt Engineering: A Systematic Review with SWOT Analysis](https://mlsanity.com/paper/2410.12843/) (2024)
- [Krait: A Backdoor Attack Against Graph Prompt Tuning](https://mlsanity.com/paper/2407.13068/) (2024)
- [A Survey of Cross-domain Graph Learning: Progress and Future Directions](https://mlsanity.com/paper/2503.11086/) (2025)
- [A Unified Pre-training and Adaptation Framework for Combinatorial Optimization on Graphs](https://mlsanity.com/paper/2312.11547/) (2023)
- [A Social-aware Gaussian Pre-trained Model for Effective Cold-start Recommendation](https://mlsanity.com/paper/2311.15790/) (2023)

## Abstract (arXiv)

Recommender systems are frequently challenged by the data sparsity problem. One approach to mitigate this issue is through cross-domain recommendation techniques. In a cross-domain context, sharing knowledge between domains can enhance the effectiveness in the target domain. Recent cross-domain methods have employed a pre-training approach, but we argue that these methods often result in suboptimal fine-tuning, especially with large neural models. Modern language models utilize prompts for efficient model tuning. Such prompts act as a tunable latent vector, allowing for the freezing of the main model parameters. In our research, we introduce the Personalised Graph Prompt-based Recommendation (PGPRec) framework. This leverages the advantages of prompt-tuning. Within this framework, we formulate personalized graph prompts item-wise, rooted in items that a user has previously engaged with. Specifically, we employ Contrastive Learning (CL) to produce pre-trained embeddings that offer greater generalizability in the pre-training phase, ensuring robust training during the tuning phase. Our evaluation of PGPRec in cross-domain scenarios involves comprehensive testing with the top-k recommendation tasks and a cold-start analysis. Our empirical findings, based on four Amazon Review datasets, reveal that the PGPRec framework can decrease the tuned parameters by as much as 74%, maintaining competitive performance. Remarkably, there's an 11.41% enhancement in performance against the leading baseline in cold-start situations.