17 citations · 29 across the 6 of their papers we have counts for
3 papers · 1 filter
EMAP: Explanation by Minimal Adversarial Perturbation
Matt Chapman-Rounds, Marc-Andre Schulz, Erik Pazos +1
Modern instance-based model-agnostic explanation methods (LIME, SHAP, L2X) are of great use in data-heavy industries for model diagnostics, and for end-user explanations. These met…
Clusters in Explanation Space: Inferring disease subtypes from model explanations
Marc-Andre Schulz, Matt Chapman-Rounds, Manisha Verma +2
Identification of disease subtypes and corresponding biomarkers can substantially improve clinical diagnosis and treatment selection. Discovering these subtypes in noisy, high dime…
Auditing and Achieving Intersectional Fairness in Classification Problems
Giulio Morina, Viktoriia Oliinyk, Julian Waton +2
Machine learning algorithms are extensively used to make increasingly more consequential decisions about people, so achieving optimal predictive performance can no longer be the on…