Causal fairness analysis
D Plecko, E Bareinboim - arxiv preprint arxiv:2207.11385, 2022 - arxiv.org
Decision-making systems based on AI and machine learning have been used throughout a
wide range of real-world scenarios, including healthcare, law enforcement, education, and …
wide range of real-world scenarios, including healthcare, law enforcement, education, and …
Equal opportunity of coverage in fair regression
We study fair machine learning (ML) under predictive uncertainty to enable reliable and
trustworthy decision-making. The seminal work of'equalized coverage'proposed an …
trustworthy decision-making. The seminal work of'equalized coverage'proposed an …
Conformalized fairness via quantile regression
Algorithmic fairness has received increased attention in socially sensitive domains. While
rich literature on mean fairness has been established, research on quantile fairness remains …
rich literature on mean fairness has been established, research on quantile fairness remains …
Reconciling predictive and statistical parity: A causal approach
Since the rise of fair machine learning as a critical field of inquiry, many different notions on
how to quantify and measure discrimination have been proposed in the literature. Some of …
how to quantify and measure discrimination have been proposed in the literature. Some of …
A fair price to pay: Exploiting causal graphs for fairness in insurance
In many jurisdictions, insurance companies are prohibited from discriminating based on
certain policyholder characteristics. Exclusion of prohibited variables from models prevents …
certain policyholder characteristics. Exclusion of prohibited variables from models prevents …
Overcoming Fairness Trade-offs via Pre-processing: A Causal Perspective
C Leininger, S Rittel, L Bothmann - arxiv preprint arxiv:2501.14710, 2025 - arxiv.org
Training machine learning models for fair decisions faces two key challenges: The\emph
{fairness-accuracy trade-off} results from enforcing fairness which weakens its predictive …
{fairness-accuracy trade-off} results from enforcing fairness which weakens its predictive …
Fair Clustering: A Causal Perspective
Clustering algorithms may unintentionally propagate or intensify existing disparities, leading
to unfair representations or biased decision-making. Current fair clustering methods rely on …
to unfair representations or biased decision-making. Current fair clustering methods rely on …
Sequential Conditional Transport on Probabilistic Graphs for Interpretable Counterfactual Fairness
In this paper, we link two existing approaches to derive counterfactuals: adaptations based
on a causal graph, as suggested in Ple\v {c} ko and Meinshausen (2020) and optimal …
on a causal graph, as suggested in Ple\v {c} ko and Meinshausen (2020) and optimal …
Training large multimodal language models with ethical values
A Roger - 2024 - papyrus.bib.umontreal.ca
The rapid expansion of artificial intelligence (AI) in modern society, exemplified by systems
like ChatGPT and Stable Diffusion, has given rise to significant ethical considerations. These …
like ChatGPT and Stable Diffusion, has given rise to significant ethical considerations. These …
Optimal Transport on Categorical Data for Counterfactuals using Compositional Data and Dirichlet Transport
Recently, optimal transport-based approaches have gained attention for deriving
counterfactuals, eg, to quantify algorithmic discrimination. However, in the general …
counterfactuals, eg, to quantify algorithmic discrimination. However, in the general …