Related papers: Model-Based Counterfactual Synthesizer for Interpr…
Machine learning can impact people with legal or ethical consequences when it is used to automate decisions in areas such as insurance, lending, hiring, and predictive policing. In many of these scenarios, previous decisions have been made…
The counterfactual token generation has been limited to perturbing only a single token in texts that are generally short and single sentences. These tokens are often associated with one of many sensitive attributes. With limited…
Applying machine learning (ML) on multivariate time series data has growing popularity in many application domains, including in computer system management. For example, recent high performance computing (HPC) research proposes a variety of…
Counterfactuals have been recognized as an effective approach to explain classifier decisions. Nevertheless, they have not yet been considered in the context of clustering. In this work, we propose the use of counterfactuals to explain…
The use of machine learning models in high-stake applications (e.g., healthcare, lending, college admission) has raised growing concerns due to potential biases against protected social groups. Various fairness notions and methods have been…
Model explanation techniques play a critical role in understanding the source of a model's performance and making its decisions transparent. Here we investigate if explanation techniques can also be used as a mechanism for scientific…
Leading approaches in machine vision employ different architectures for different tasks, trained on costly task-specific labeled datasets. This complexity has held back progress in areas, such as robotics, where robust task-general…
Counterfactual explanations elucidate algorithmic decisions by pointing to scenarios that would have led to an alternative, desired outcome. Giving insight into the model's behavior, they hint users towards possible actions and give grounds…
The adoption of increasingly complex deep models has fueled an urgent need for insight into how these models make predictions. Counterfactual explanations form a powerful tool for providing actionable explanations to practitioners.…
Access to real clinical data is often restricted due to privacy obligations, creating significant barriers for healthcare research. Synthetic datasets provide a promising solution, enabling secure data sharing and model development.…
Data-driven decision making frequently relies on predicting counterfactual outcomes. In practice, researchers commonly train counterfactual prediction models on a source dataset to inform decisions on a possibly separate target population.…
Interventions targeting the representation space of language models (LMs) have emerged as an effective means to influence model behavior. Such methods are employed, for example, to eliminate or alter the encoding of demographic information…
We develop a novel method for counterfactual analysis based on observational data using prediction intervals for units under different exposures. Unlike methods that target heterogeneous or conditional average treatment effects of an…
The discovery of patient-specific imaging markers that are predictive of future disease outcomes can help us better understand individual-level heterogeneity of disease evolution. In fact, deep learning models that can provide data-driven…
Accurate prediction of solar energetic particle events is vital for safeguarding satellites, astronauts, and space-based infrastructure. Modern space weather monitoring generates massive volumes of high-frequency, multivariate time series…
Facial analysis models are increasingly used in applications that have serious impacts on people's lives, ranging from authentication to surveillance tracking. It is therefore critical to develop techniques that can reveal unintended biases…
Counterfactual data augmentation has recently emerged as a method to mitigate confounding biases in the training data. These biases, such as spurious correlations, arise due to various observed and unobserved confounding variables in the…
Most machine learning (ML) models are developed for prediction only; offering no option for causal interpretation of their predictions or parameters/properties. This can hamper the health systems' ability to employ ML models in clinical…
Counterfactual explanations have been successfully applied to create human interpretable explanations for various black-box models. They are handy for tasks in the image domain, where the quality of the explanations benefits from recent…
Counterfactual Explanations (CEs) help address the question: How can the factors that influence the prediction of a predictive model be changed to achieve a more favorable outcome from a user's perspective? Thus, they bear the potential to…