Fairness-aware learning aims at constructing classifiers that not only make accurate predictions, but also do not discriminate against specific groups. It is a fast-growing area of …
X Wang, H Huang - arXiv preprint arXiv:1909.03013, 2019 - arxiv.org
Fairness is becoming a rising concern wrt machine learning model performance. Especially for sensitive fields such as criminal justice and loan decision, eliminating the prediction …
Differentially-private mechanisms for text generation typically add carefully calibrated noise to input words and use the nearest neighbor to the noised input as the output word. When …
Building machine learning models that are fair with respect to an unprivileged group is a topical problem. Modern fairness-aware algorithms often ignore causal effects and enforce …
As machine learning algorithms grow in popularity and diversify to many industries, ethical and legal concerns regarding their fairness have become increasingly relevant. We explore …
C Matzken, S Eger, I Habernal - arXiv preprint arXiv:2305.14936, 2023 - arxiv.org
Protecting privacy in contemporary NLP models is gaining in importance. So does the need to mitigate social biases of such models. But can we have both at the same time? Existing …
Given the increasing importance of machine learning (ML) in our lives, several algorithmic fairness techniques have been proposed to mitigate biases in the outcomes of the ML …
J Sohn, Q Song, G Lin - International Conference on Artificial …, 2024 - proceedings.mlr.press
As the data-driven decision process becomes dominating for industrial applications, fairness- aware machine learning arouses great attention in various areas. This work proposes …
F Branchaud-Charron, P Atighehchian… - arXiv preprint arXiv …, 2021 - arxiv.org
Dataset bias is one of the prevailing causes of unfairness in machine learning. Addressing fairness at the data collection and dataset preparation stages therefore becomes an …