相关论文: Wasserstein-based fairness interpretability framew…

We propose a fair machine learning algorithm to model interpretable differences between observed and desired human decision-making, with the latter aimed at reducing disparity in a downstream outcome impacted by the human decision. Prior…

Modern statistical learning techniques have often emphasized prediction performance over interpretability, giving rise to "black box" models that may be difficult to understand, and to generalize to other settings. We conceptually divide a…

The Wasserstein distance has emerged as a key metric to quantify distances between probability distributions, with applications in various fields, including machine learning, control theory, decision theory, and biological systems.…

Fairness-aware learning aims to mitigate discrimination against specific protected social groups (e.g., those categorized by gender, ethnicity, age) while minimizing predictive performance loss. Despite efforts to improve fairness in…

Current methodologies in machine learning analyze the effects of various statistical parity notions of fairness primarily in light of their impacts on predictive accuracy and vendor utility loss. In this paper, we propose a new framework…

Conformal prediction methods provide statistically rigorous marginal coverage guarantees for machine learning models, but such guarantees fail to account for algorithmic biases, thereby undermining fairness and trust. This paper introduces…

While machine learning models have achieved unprecedented success in real-world applications, they might make biased/unfair decisions for specific demographic groups and hence result in discriminative outcomes. Although research efforts…

The paper proposes a new approach to model risk measurement based on the Wasserstein distance between two probability measures. It formulates the theoretical motivation resulting from the interpretation of fictitious adversary of robust…

The growing use of Machine Learning (ML) tools comes with critical challenges, such as limited model explainability. We propose a global explainability framework that leverages Optimal Transport and Distributionally Robust Optimization to…

Algorithm fairness has become a central problem for the broad adoption of artificial intelligence. Although the past decade has witnessed an explosion of excellent work studying algorithm biases, achieving fairness in real-world AI…

Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability. Conventional fairness interventions typically require access to sensitive attributes like gender or race, but…

Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity…

We consider the problem of how decision making can be fair when the underlying probabilistic model of the world is not known with certainty. We argue that recent notions of fairness in machine learning need to explicitly incorporate…

Machine Learning techniques have become pervasive across a range of different applications, and are now widely used in areas as disparate as recidivism prediction, consumer credit-risk analysis and insurance pricing. The prevalence of…

Artificial intelligence supports healthcare professionals with predictive modeling, greatly transforming clinical decision-making. This study addresses the crucial need for fairness and explainability in AI applications within healthcare to…

We study the problem of network regression, where one is interested in how the topology of a network changes as a function of Euclidean covariates. We build upon recent developments in generalized regression models on metric spaces based on…

It is now well understood that machine learning models, trained on data without due care, often exhibit unfair and discriminatory behavior against certain populations. Traditional algorithmic fairness research has mainly focused on…

Algorithmic fairness has aroused considerable interests in data mining and machine learning communities recently. So far the existing research has been mostly focusing on the development of quantitative metrics to measure algorithm…

As machine learning is increasingly used to make real-world decisions, recent research efforts aim to define and ensure fairness in algorithmic decision making. Existing methods often assume a fixed set of observable features to define…

Machine learning models in safety-critical settings like healthcare are often blackboxes: they contain a large number of parameters which are not transparent to users. Post-hoc explainability methods where a simple, human-interpretable…