Related papers: SparCAssist: A Model Risk Assessment Assistant Bas…

In this thesis we discuss machine learning methods performing automated variable selection for learning sparse predictive models. There are multiple reasons for promoting sparsity in the predictive models. By relying on a limited set of…

Counterfactual explanations for machine learning models are used to find minimal interventions to the feature values such that the model changes the prediction to a different output or a target output. A valid counterfactual explanation…

Counterfactual explanations provide an intuitive way to understand model decisions by identifying minimal changes required to alter an outcome. However, applying counterfactual methods to time series models remains challenging due to…

Machine learning models that automate decision-making are increasingly being used in consequential areas such as loan approvals, pretrial bail approval, hiring, and many more. Unfortunately, most of these models are black-boxes, i.e., they…

Machine-learning models are increasingly driving decisions in high-stakes settings, such as finance, law, and hiring, thus, highlighting the need for transparency. However, the key challenge is to balance transparency -- clarifying `why' a…

Counterfactual explanations are a common tool to explain artificial intelligence models. For Reinforcement Learning (RL) agents, they answer "Why not?" or "What if?" questions by illustrating what minimal change to a state is needed such…

Surrogate models are used to alleviate the computational burden in engineering tasks, which require the repeated evaluation of computationally demanding models of physical systems, such as the efficient propagation of uncertainties. For…

Counterfactual Explanations (CEs) are a powerful technique used to explain Machine Learning models by showing how the input to a model should be minimally changed for the model to produce a different output. Similar proposals have been made…

We study counterfactual classification as a new tool for decision-making under hypothetical (contrary to fact) scenarios. We propose a doubly-robust nonparametric estimator for a general counterfactual classifier, where we can incorporate…

Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, prior work has not explored how these methods can be…

One of the primary challenges limiting the applicability of deep learning is its susceptibility to learning spurious correlations rather than the underlying mechanisms of the task of interest. The resulting failure to generalise cannot be…

Monitoring unexpected health events and taking actionable measures to avert them beforehand is central to maintaining health and preventing disease. Therefore, a tool capable of predicting adverse health events and offering users actionable…

Latent Class Analysis (LCA) is widely used to identify unobserved subgroups in social and behavioural sciences. A long-standing challenge for LCA is the interpretability of the latent classes, due to the high complexity of the estimated…

Counterfactuals operationalised through algorithmic recourse have become a powerful tool to make artificial intelligence systems explainable. Conceptually, given an individual classified as y -- the factual -- we seek actions such that…

Many natural signals exhibit a sparse representation, whenever a suitable describing model is given. Here, a linear generative model is considered, where many sparsity-based signal processing techniques rely on such a simplified model. As…

We propose answer-set programs that specify and compute counterfactual interventions as a basis for causality-based explanations to decisions produced by classification models. They can be applied with black-box models and models that can…

Counterfactual examples (CFs) are one of the most popular methods for attaching post-hoc explanations to machine learning (ML) models. However, existing CF generation methods either exploit the internals of specific models or depend on each…

In Artificial Intelligence, interpreting the results of a Machine Learning technique often termed as a black box is a difficult task. A counterfactual explanation of a particular "black box" attempts to find the smallest change to the input…

The inevitable appearance of spurious correlations in training datasets hurts the generalization of NLP models on unseen data. Previous work has found that datasets with paired inputs are prone to correlations between a specific part of the…

To truly grasp reasoning ability, a Natural Language Inference model should be evaluated on counterfactual data. TabPert facilitates this by assisting in the generation of such counterfactual data for assessing model tabular reasoning…