User Item Interaction

User-item interaction research focuses on understanding and modeling how users engage with items in various systems, aiming to improve recommendation accuracy and personalization. Current research emphasizes addressing data noise and biases in implicit feedback, incorporating user intent and long-term preferences through techniques like contrastive learning, graph neural networks, and large language models (LLMs), and developing more efficient training methods for large datasets. These advancements are crucial for enhancing recommender systems across diverse applications, from e-commerce and entertainment to education, by providing more relevant and unbiased recommendations.