Carlos Scheidegger

is this you? claim profile

0 followers
The University of Arizona ∙ Carlos Scheidegger

Problems with Shapley-value-based explanations as feature importance measures

Game-theoretic formulations of feature importance have become popular as...
02/25/2020 ∙ by I. Elizabeth Kumar, et al. ∙ 19 ∙ share

read it
Anteater: Interactive Visualization for Program Understanding

Understanding and debugging long, complex programs can be extremely diff...
07/05/2019 ∙ by Rebecca Faust, et al. ∙ 0 ∙ share

read it
Disentangling Influence: Using Disentangled Representations to Audit Model Predictions

Motivated by the need to audit complex and black box models, there has b...
06/20/2019 ∙ by Charles T. Marx, et al. ∙ 8 ∙ share

read it
Assessing the Local Interpretability of Machine Learning Models

The increasing adoption of machine learning tools has led to calls for a...
02/09/2019 ∙ by Sorelle A. Friedler, et al. ∙ 0 ∙ share

read it
Fairness in representation: quantifying stereotyping as a representational harm

While harms of allocation have been increasingly studied as part of the ...
01/28/2019 ∙ by Mohsen Abbasi, et al. ∙ 8 ∙ share

read it
NNCubes: Learned Structures for Visual Data Exploration

Visual exploration of large multidimensional datasets has seen tremendou...
08/27/2018 ∙ by Zhe Wang, et al. ∙ 0 ∙ share

read it
Homology-Preserving Dimensionality Reduction via Manifold Landmarking and Tearing

Dimensionality reduction is an integral part of data visualization. It i...
06/22/2018 ∙ by Lin Yan, et al. ∙ 0 ∙ share

read it
A comparative study of fairness-enhancing interventions in machine learning

Computers are increasingly used to make decisions that have significant ...
02/13/2018 ∙ by Sorelle A. Friedler, et al. ∙ 0 ∙ share

read it
Driving Interactive Graph Exploration Using 0-Dimensional Persistent Homology Features

Graphs are commonly used to encode relationships among entities, yet, th...
12/15/2017 ∙ by Ashley Suh, et al. ∙ 0 ∙ share

read it
DimReader: Using auto-differentiation to explain non-linear projections

Non-linear dimensionality reduction (NDR) methods such as LLE and t-SNE ...
10/03/2017 ∙ by Rebecca Faust, et al. ∙ 0 ∙ share

read it
Visual Detection of Structural Changes in Time-Varying Graphs Using Persistent Homology

Topological data analysis is an emerging area in exploratory data analys...
07/20/2017 ∙ by Mustafa Hajij, et al. ∙ 0 ∙ share

read it
Runaway Feedback Loops in Predictive Policing

Predictive policing systems are increasingly used to determine how to al...
06/29/2017 ∙ by Danielle Ensign, et al. ∙ 0 ∙ share

read it
On the (im)possibility of fairness

What does it mean for an algorithm to be fair? Different papers use diff...
09/23/2016 ∙ by Sorelle A. Friedler, et al. ∙ 0 ∙ share

read it
Auditing Black-box Models for Indirect Influence

Data-trained predictive models see widespread use, but for the most part...
02/23/2016 ∙ by Philip Adler, et al. ∙ 0 ∙ share

read it
Certifying and removing disparate impact

What does it mean for an algorithm to be biased? In U.S. law, unintentio...
12/11/2014 ∙ by Michael Feldman, et al. ∙ 0 ∙ share

read it

Carlos Scheidegger

Featured Co-authors

Zhe Wang

Bei Wang

Suresh Venkatasubramanian

Mustafa Hajij

Paul Rosen

Remco Chang

Matthew Berger

Sorelle A. Friedler

Joshua A. Levine

Dylan Slack

Dylan Cashman

Problems with Shapley-value-based explanations as feature importance measures

Anteater: Interactive Visualization for Program Understanding

Disentangling Influence: Using Disentangled Representations to Audit Model Predictions

Assessing the Local Interpretability of Machine Learning Models

Fairness in representation: quantifying stereotyping as a representational harm

NNCubes: Learned Structures for Visual Data Exploration

Homology-Preserving Dimensionality Reduction via Manifold Landmarking and Tearing

A comparative study of fairness-enhancing interventions in machine learning

Driving Interactive Graph Exploration Using 0-Dimensional Persistent Homology Features

DimReader: Using auto-differentiation to explain non-linear projections

Visual Detection of Structural Changes in Time-Varying Graphs Using Persistent Homology

Runaway Feedback Loops in Predictive Policing

On the (im)possibility of fairness

Auditing Black-box Models for Indirect Influence

Certifying and removing disparate impact