Exposure Fairness

Exposure fairness research aims to mitigate biases in algorithmic systems that disproportionately affect certain groups, ensuring equitable representation and access to information or opportunities. Current work focuses on developing metrics to quantify bias in ranked lists and recommender systems, exploring algorithms like UCB-based methods for stochastic bandits and fairness-aware Vision Transformers with debiasing techniques, and extending fairness considerations beyond individual items or users to encompass group-level interactions. This research is crucial for addressing societal harms stemming from algorithmic bias, impacting fields like information retrieval, computer vision, and online platforms by promoting more equitable and just outcomes.

Papers

March 9, 2024

Measuring Bias in a Ranked List using Term-based Representations
Amin Abolghasemi, Leif Azzopardi, Arian Askari, Maarten de Rijke, Suzan Verberne
Fairness Evaluation Ranking Task Passage Reranking Quantifying Bias Unbiased Evaluation Ranking Fairness Term Representation Exposure Fairness

February 8, 2024

Simultaneously Achieving Group Exposure Fairness and Within-Group Meritocracy in Stochastic Bandits
Subham Pokhriyal, Shweta Jain, Ganesh Ghalme, Swapnil Dhamal, Sujit Gujar
Stochastic Bandit Individual Fairness Stochastic Multi Armed Bandit Fairness Performance Exposure Fairness

January 31, 2023

Fairness-aware Vision Transformer via Debiased Self-Attention
Yao Qiang, Chengyin Li, Prashant Khanduri, Dongxiao Zhu
Vision Transformer Bias Mitigation Attention Regularization Attention Bias Exposure Fairness

April 29, 2022

Joint Multisided Exposure Fairness for Recommendation
Haolun Wu, Bhaskar Mitra, Chen Ma, Fernando Diaz, Xue Liu
Effective Recommendation Exposure Fairness

Exposure Fairness

Papers

Measuring Bias in a Ranked List using Term-based Representations

Simultaneously Achieving Group Exposure Fairness and Within-Group Meritocracy in Stochastic Bandits

Fairness-aware Vision Transformer via Debiased Self-Attention

Joint Multisided Exposure Fairness for Recommendation