IMETA-GNN: Meta Learning-Based Cold Start Optimization for Recommendation System

Recommendation systems are becoming essential components of contemporary online goods and services, and they significantly affect customer satisfaction. Recommendation systems are designed to empower customers in their decision-making process by providing personalized recommendations. Meta-learning has proven to be effective in addressing user cold-start problem in recommendation systems. Many meta learning based recommendation systems designed for the cold-start problem are gradient-based. The existing frameworks require optimization techniques to maximize potential of hyper networks, enabling them to adapt and generate compatible parameters for efficient learning as meta-learners. However, these frameworks often lack contextual knowledge from users to provide suitable initial guidelines in the recommendation network for new users. We propose a framework that optimizes the cold-start problem using a meta-learning approach to improve accuracy of recommendation systems. Our approach generates personalized recommendations by considering users’ past behavior and preferences, thereby enhancing the accuracy and fine-tuning of product recommendations.We have evaluated the proposed IMETA-GNN model on two datasets namely Movielens 100k and DBook, and accuracy obtained is 82% and 75% respectively. The performance evaluation demonstrate that our proposed method outperforms several state-of-the-art meta-learning recommendation systems in addressing the user cold-start conundrum.