Counterfactual Fairness
Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made that are unfairly biased against certain subpopulations, for example those of a particular race, gender, or sexual orientation. Since this past data may be biased, machine learning predictors must account for this to avoid perpetuating or creating discriminatory practices. In this work, we develop a framework for modeling fairness using tools from causal inference. Our definition of counterfactual fairness} captures the intuition that a decision is fair towards an individual if it is the same in (a) the actual world and (b) a counterfactual world where the individual belonged to a different demographic group. We demonstrate our framework on a real-world problem of fair prediction of success in law school.
See more at https://www.microsoft.com/en-us/research/video/counterfactual-fairness/
Видео Counterfactual Fairness канала Microsoft Research
See more at https://www.microsoft.com/en-us/research/video/counterfactual-fairness/
Видео Counterfactual Fairness канала Microsoft Research
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Counterfactual Fairness: Matt Kusner, The Alan Turing InstituteCausal Models for Algorithmic Fairness - Ricardo SilvaGraph neural networks: Variations and applicationsAlgorithmic Bias and Fairness: Crash Course AI #18Counterfactual Evaluation and Learning from Logged User FeedbackThe Math Needed for Computer ScienceFireside Chat with Cynthia Dwork14.1 - CounterfactualsAI for Imperfect-Information Games: Beating Top Humans in No-Limit PokerFairness, part 1 - Moritz Hardt - MLSS 2020, TübingenArithmetic coding ProcedureYann LeCun - Power & Limits of Deep LearningTech Talk: Poker AI: Libratus and an Introduction to Counterfactual Regret MinimizationHow Deep Neural Networks WorkNeural Models for Information RetrievalCounterfactual Multi-Agent Policy GradientsGraph Databases Will Change Your Freakin' Life (Best Intro Into Graph Databases)How to Write an Effective Research PaperGeneralizing Convolutions for Deep Learning