Item Enhanced Diversification in the Recommendation System using Graph Neural Network

Abstract

A recommendation system is a set of programs that utilize different methodologies for relevant item selection for the user. Graph neural networks have been extensively used in recent years to improve the quality of recommendations across all domains. A general recommendation system’s main goal is to recommend items to the user accurately, and it frequently prioritizes items that are well-liked or mainstream. If the model concentrates only on one specific item category from the users’ past preferences, then recommendations for the target user will become too obvious. To address this problem, diversity in the recommendation system is introduced. The model IG-DivRS (Item-Enhanced Graph Neural Network for a Diversified Recommendation System) is proposed. Our proposed model uses a Graph Neural Network (GNN) with the user’s interacted and non-interacted item history for diversified recommendation generation. The novelty of our proposed model is to explore the effect of non-interacted items on the target user for diversified recommendation generation. Instead of selecting random non-interacted items for the target user, we apply the DPP(Determinantal Point Process) algorithm to select the non-interacted item appropriately. The detailed experimental analysis shows that our model ID-DivRS outperforms the state-of-the-art model in accuracy and diversity.