Machine learning plays a role in many deployed decision systems, often in ways that are
difficult or impossible to understand by human stakeholders. Explaining, in a human …

The rise of sophisticated black-box machine learning models in Artificial Intelligence
systems has prompted the need for explanation methods that reveal how these models work …

With the power of parallel processing, large datasets, and fast computational resources,
deep neural networks (DNNs) have outperformed highly trained and experienced human …

Counterfactual explanations inform ways to achieve a desired outcome from a machine
learning model. However, such explanations are not robust to certain real-world changes in …

In this work, we present Fairness Aware Counterfactuals for Subgroups (FACTS), a
framework for auditing subgroup fairness through counterfactual explanations. We start with …

There is an emerging interest in generating robust algorithmic recourse that would remain
valid if the model is updated or changed even slightly. Towards finding robust algorithmic …

The main objective of this thesis is to increase trust in Machine Learning models by
developing tools capable of explaining their predictions and quantifying the associated …

Graph Neural Networks (GNNs) have been widely deployed in various real-world
applications. However, most GNNs are black-box models that lack explanations. One …

Counterfactual explanations (CE) identify data points that closely resemble the observed
data but produce different machine learning (ML) model outputs, offering critical insights into …

Growing regulatory and societal pressures demand increased transparency in AI,
particularly in understanding the decisions made by complex machine learning models …