Search Results for author:
Found 2 papers, 0 papers with code
Explainability for fair machine learning
Moreover, motivated by the linearity of Shapley explainability, we propose a meta algorithm for applying existing training-time fairness interventions, wherein one trains a perturbation to the original model, rather than a new model entirely.
Shapley explainability on the data manifold
Explainability in AI is crucial for model development, compliance with regulation, and providing operational nuance to predictions.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
