Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems
(IEEE S&P) Evaluate the individual, joint and marginal influence of features on a model using shapley values.
- from
- Audit Algorithms
- added
- 2026-10-10
- likes
- 0
similar
-
Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems ieeexplore.ieee.org
(Security and Privacy) Introduces measures that capture the degree of influence of inputs on outputs of the observed system.
-
Auditing Black-Box Models for Indirect Influence arxiv.org
(ICDM) Evaluate the influence of a variable on a black-box model by "cleverly" removing it from the dataset and looking at the accuracy gap
-
-
-
Shalev-Shwartz. Understanding Machine Learning: From Theory to Algorithms cambridge.org
It provides an extensive theoretical account of the fundamental ideas underlying machine learning and the mathematical derivations that transform these principles into practical algorithms.
-
Shapley github.com
A data-driven framework to quantify the value of classifiers in a machine learning ensemble.
Audit Algorithms › Papers > 2016: “(IEEE S&P) Evaluate the individual, joint and marginal influence of features on a model using shapley values.”