Modern Recommender System
Modern recommender systems aim to provide users with personalized and relevant item suggestions, addressing challenges like scalability, real-time performance, and user engagement. Current research focuses on improving efficiency through techniques like optimized loss functions and caching strategies, enhancing user experience with diverse and relevant recommendations using reinforcement learning and hierarchical models, and increasing transparency and control through explainable AI and counterfactual reasoning. These advancements have significant implications for various applications, improving user satisfaction and enabling more effective knowledge exploration and resource allocation in diverse online platforms.
Papers
September 27, 2024
September 20, 2024
September 11, 2024
August 7, 2024
August 5, 2024
March 11, 2024
February 10, 2024
February 5, 2024
January 31, 2024
January 17, 2024
October 17, 2023
September 24, 2023
September 8, 2023
September 4, 2023
August 11, 2023
August 2, 2023
November 28, 2022
November 27, 2022
October 17, 2022
October 11, 2022