PT4Rec: A Universal Prompt-Tuning Framework for Graph Contrastive Learning-Based Recommendations

Abstract

Graph contrastive learning-based recommendations have attracted a lot of research attention due to their exceptional performance. However, these approaches, which hinge on the optimization of downstream recommendations, often deviate from the original purpose of graph contrastive learning (i.e., learning embeddings independently of downstream tasks) and result in inconsistent performance. Some researchers have attempted to address this issue through prompt tuning, but the use of single and fixed prompts has shown limited efficacy and a lack of robustness across various benchmarks. To bridge the gap between graph contrastive learning and recommendation tasks, this paper proposes a universal Prompt-Tuning framework called PT4Rec. PT4Rec constructs learnable multi-prompts to capitalize on the flexibility of prompt tuning, thereby enhancing the robustness of graph contrastive learning-based recommendations in different scenarios. Specifically, PT4Rec first employs graph contrastive learning to enhance the pre-training embeddings of user and item nodes. Then it integrates multiple prompts derived from user profile inputs with user embeddings by the attention mechanism for prompt-tuning on downstream recommendation tasks. PT4Rec extends the prompt-tuning technique to adapt to various recommendation scenarios and constructs learnable multi-prompts to achieve better recommendation performance and scalability. Experimental validation on four benchmark datasets demonstrates the effectiveness of PT4Rec. The code is released at https://github.com/xiaowei-i/PT4Rec .