Achieving Fairness via Post-Processing in Web-Scale Recommender Systems
원문 초록
Building fair recommender systems is a challenging and crucial area of study due to its immense impact on society. We extended the definitions of two commonly accepted notions of fairness to recommender systems, namely equality of opportunity and equalized odds. These fairness measures ensure that equally "qualified" (or "unqualified") candidates are treated equally regardless of their protected attribute status (such as gender or race). We propose scalable methods for achieving equality of opportunity and equalized odds in rankings in the presence of position bias, which commonly plagues data generated from recommender systems. Our algorithms are model agnostic in the sense that they depend only on the final scores provided by a model, making them easily applicable to virtually all web-scale recommender systems. We conduct extensive simulations as well as real-world experiments to show the efficacy of our approach.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
A Reproducibility Study of Product-side Fairness in Bundle Recommendation
Robustly Improving LLM Fairness in Realistic Settings via Interpretability
Improving Fairness of Large Language Models in Multi-document Summarization
Addressing Correlated Latent Exogenous Variables in Debiased Recommender Systems
Looking for Fairness in Recommender Systems
Journalism-Guided Agentic In-Context Learning for News Stance Detection
토론
이 논문과 연결된 포럼 글이 아직 없습니다.