Explore a cutting-edge conference talk on configurable fairness in recommender systems, focusing on new item recommendations and entry time considerations. Delve into the research presented by authors Huizhong Guo, Dongxia Wang, Zhu Sun, Haonan Zhang, Jinfeng Li, and Jie Zhang as they address the challenges of fairness in RecSys. Learn about innovative approaches to balancing recommendation accuracy with fair exposure for newly introduced items, taking into account their entry time into the system. Gain insights into the latest advancements in creating more equitable and effective recommendation algorithms that can adapt to the dynamic nature of item catalogs.
Configurable Fairness for New Item Recommendation Considering Entry Time - SIGIR 2024
Association for Computing Machinery (ACM) via YouTube
Overview
Syllabus
SIGIR 2024 M1.7 [fp] Configurable Fairness for New Item Recommendation Considering Entry Time
Taught by
Association for Computing Machinery (ACM)
Related Courses
-
Fair Sequential Recommendation without User Demographics - SIGIR 2024
-
Adaptive Fair Representation Learning for Personalized Fairness in Recommendations - Lecture 7
-
CaDRec: Contextualized and Debiased Recommender Model - Fairness in RecSys
-
Fair Recommendations with Limited Sensitive Attributes - A Distributionally Robust Optimization Approach
-
Going Beyond Popularity and Positivity Bias: Correcting Multifactorial Bias in Recommender Systems - M1.7
-
Can We Trust Recommender System Fairness Evaluation? The Role of Fairness and Relevance - Evaluation M1.5
