
-
Problems with Shapley-value-based explanations as feature importance measures
Game-theoretic formulations of feature importance have become popular as...
read it
-
Anteater: Interactive Visualization for Program Understanding
Understanding and debugging long, complex programs can be extremely diff...
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...
read it
-
Assessing the Local Interpretability of Machine Learning Models
The increasing adoption of machine learning tools has led to calls for a...
read it
-
Fairness in representation: quantifying stereotyping as a representational harm
While harms of allocation have been increasingly studied as part of the ...
read it
-
NNCubes: Learned Structures for Visual Data Exploration
Visual exploration of large multidimensional datasets has seen tremendou...
read it
-
Homology-Preserving Dimensionality Reduction via Manifold Landmarking and Tearing
Dimensionality reduction is an integral part of data visualization. It i...
read it
-
A comparative study of fairness-enhancing interventions in machine learning
Computers are increasingly used to make decisions that have significant ...
read it
-
Driving Interactive Graph Exploration Using 0-Dimensional Persistent Homology Features
Graphs are commonly used to encode relationships among entities, yet, th...
read it
-
DimReader: Using auto-differentiation to explain non-linear projections
Non-linear dimensionality reduction (NDR) methods such as LLE and t-SNE ...
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...
read it
-
Runaway Feedback Loops in Predictive Policing
Predictive policing systems are increasingly used to determine how to al...
read it
-
On the (im)possibility of fairness
What does it mean for an algorithm to be fair? Different papers use diff...
read it
-
Auditing Black-box Models for Indirect Influence
Data-trained predictive models see widespread use, but for the most part...
read it
-
Certifying and removing disparate impact
What does it mean for an algorithm to be biased? In U.S. law, unintentio...
read it