Oct 14, 2020 · In this work we present a new approach to explaining fairness in machine learning, based on the Shapley value paradigm. Our fairness ...
scholar.google.com › citations
The goal of the paper is to design mechanisms to explain the unfairness in the outcomes of a ML model and propose methods to mitigate unfairness. The paper uses ...
In this section we give an overview of the Shapley value paradigm for machine learning explainability, and show how it can be adapted to explain fairness.
People also ask
What is explainability in machine learning?
What is fair machine learning?
How do you measure fairness in machine learning models?
What is the basic difference between ML interpretability and ML explainability?
Our paper explores the practical implications and effectiveness of four bias mitigation algorithms (learning fair representations, reweighing, Equality of Odds ...
This work presents a new approach to explaining fairness in machine learning, based on the Shapley value paradigm, and proposes a meta algorithm for ...
Jun 12, 2023 · In this dissertation, we present 5 research projects that aim to enhance explainability and fairness in classification systems and word embeddings.
We evaluate several algorithms for a fair and explainable recommendation system that predicts whether a loan request on Kiva.org will be completely funded or ...
Ensuring fairness in machine learning models is hard, in no small part because even simply determining what "unfairness" should mean in a given context is.
Apr 17, 2022 · The explainability requires that an AI system provides a human-understandable explanation of why any given decision was reached in terms of the ...
This policy analysis explores the regulatory and public policy implications of the increasing use of machine learning models and explainability and fairness ...