Tag Aware Recommendation
Tag-aware recommendation systems aim to improve personalized recommendations by leveraging user-provided tags associated with items. Current research focuses on enhancing these systems using techniques like graph neural networks (GNNs) to capture relationships between users, items, and tags, and incorporating large language models (LLMs) to better understand tag semantics and user preferences. These advancements address limitations in existing methods, such as handling sparse data and diverse user interests, leading to more accurate and relevant recommendations in various applications, including e-commerce and social media. The improved efficiency and effectiveness of these models are key areas of ongoing investigation.
Papers
November 10, 2024
June 20, 2024
June 17, 2024
July 6, 2023
November 11, 2022