Improving Fair Training under Correlation Shifts
24. července 2023
Řečníci
Kangwook Lee
Řečník · 0 sledujících
Steven E. Whang
Řečník · 0 sledujících
Changho Suh
Řečník · 0 sledujících
O prezentaci
Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in practice. In particular, when the bias between labels and sensitive groups changes, the fairness of the trained model is directly influenced and can worsen. We make two contributions for solving this problem. First, we analytically show that existing in-processing fair algorithms have fundamental limits in accuracy and group fairness. We introduce the notion of correlation shifts, which can explicitly capture the change of the above bias. Second, we propose a novel pre-processing step that samples the input data to reduce correlation shifts and thus enables the in-processing approaches to overcome their limitations. We formulate an optimization problem for adjusting the data ratio among labels and sensitive groups to reflect the shifted correlation. A key benefit of our approach lies in decoupling the roles of pre- and in-processing approaches: correlation adjustment via pre-processing and unfairness mitigation on the processed data via in-processing. Experiments show that our framework effectively improves existing in-processing fair algorithms w.r.t. accuracy and fairness, both on synthetic and real datasets.Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in practice. In particular, when the bias between labels and sensitive groups changes, the fairness of the trained model is directly influenced and can worsen. We make two contributions for solving this problem. First, we analytically show that existing in-processing f…
Baví vás formát? Nechte SlidesLive zachytit svou akci!
Profesionální natáčení a streamování po celém světě.
Sdílení
Doporučená videa
Prezentace na podobné téma, kategorii nebo přednášejícího
Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere
Zhlédnout později
Boris Bonev, …
Special Properties of Gradient Descent with Large Learning Rates
Zhlédnout později
Vector-valued Control Variates
Zhlédnout později
Zhuo Sun, …
Vertical Federated Graph Neural Network for Recommender System
Zhlédnout později
Peihua Mai, …
RACE: Improve Multi-Agent Reinforcement Learning with Representation Asymmetry and Collaborative Evolution
Zhlédnout později
Pengyi Li, …
