Contrastive Graph Prompt-tuning for Cross-domain Recommendation

Abstract

Recommender systems commonly suffer from the long-standing data sparsity problem where insufficient user-item interaction data limits the systems’ ability to make accurate recommendations. This problem can be alleviated using cross-domain recommendation techniques. In particular, in a cross-domain setting, knowledge sharing between domains permits improved effectiveness on the target domain. While recent cross-domain recommendation techniques used a pre-training configuration, we argue that such techniques lead to a low fine-tuning efficiency, especially when using large neural models. In recent language models, prompts have been used for parameter-efficient and time-efficient tuning of the models on the downstream tasks - these prompts represent a tunable latent vector that permits to freeze the rest of the language model’s parameters. To address the cross-domain recommendation task in an efficient manner, we propose a novel Personalised Graph Prompt-based Recommendation (PGPRec) framework, which leverages the efficiency benefits from prompt-tuning. In such a framework, we develop personalised and item-wise graph prompts based on relevant items to those items the user has interacted with. In particular, we apply Contrastive Learning (CL) to generate the pre-trained embeddings, to allow an increased generalisability in the pre-training stage and to ensure an effective prompt-tuning stage. To evaluate the effectiveness of our PGPRec framework in a cross-domain setting, we conduct an extensive evaluation with the top- k recommendation task and perform a cold-start analysis. The obtained empirical results on four Amazon Review datasets show that our proposed PGPRec framework can reduce up to 74% of the tuned parameters with a competitive performance and achieves an 11.41% improved performance compared to the strongest baseline in a cold-start scenario.

Deep Semantic-Level Cross-Domain Recommendation Model Based on DSV-CDRM

“…A Triple Sequence Learning (Tri-CDR) model for cross-domain recommendation was proposed (Ma et al, 2023) that achieves precise mining of triple correlations by jointly modeling source domain, target domain, and mixed behavior while considering the global information of recommendation items and user target preferences. A personalized graph prompt recommendation (PGPRec) framework for CDR has been proposed (Yi et al, 2023) that utilizes prompt adjustment to solve the user cold-start problem and improve the training efficiency of the model. The comparison of the latest CDR models is listed in Table 1.…”

MultiGPrompt for Multi-Task Pre-Training and Prompting on Graphs

“…Not surprisingly, different pretext tasks capture different self-supervised signals from the graph. For example, link prediction tasks are more concerned with the connectivity or relationship between nodes [40], node/edge featurebased tasks focus more on the feature space [42], and subgraphbased tasks focus more on local or global information [30,55]. To cater to diverse downstream tasks, the pre-training step should aim to broadly extract knowledge from various aspects, such as node connectivity, node or edge features, and local or global graph patterns.…”