Machine learning (ML) methods are increasingly being used to develop prediction models as their use often yields models with superior predictive performance compared to models developed using traditional statis
One of the problems in development of fair machine learning methods is the non-differentiability of group fairness metrics. The first method used to directly optimize constrained non-differentiable problems is based on proxy-Lagrangian formulation of constrained Lagrangian function (Cotter et al., 2019...
“In machine learning, it is common to blame the data for bias in models. But we don’t always have balanced data. So, we need to come up with methods that actually fix the problem with imbalanced data,” says lead author Natalie Dullerud, a graduate student ...
FAIR Chemistry's library of machine learning methods for chemistry - GitHub - FAIR-Chem/fairchem: FAIR Chemistry's library of machine learning methods for chemistry
The widespread implementation of machine learning in safety-critical domains has raised ethical concerns regarding algorithmic discrimination. In such sett
Drago Plečko and Elias Bareinboim (2024), "Causal Fairness Analysis: A Causal Toolkit for Fair Machine Learning", Foundations and Trends® in Machine Learning: Vol. 17: No. 3, pp 304-589. http://dx.doi.org/10.1561/2200000106 Export ...
As discussed in the methods, this is due to data challenges, but incorporating additional criteria into the model so that under certain circumstances a switch suggestion cannot be given is an avenue for future work. However, we believe by anayzing and summarising multiple variables regarding the ...
Kernel methods 1Introduction “Perfect objectivity is an unrealistic goal; fairness, however, is not.”–M. Pollan, 2004 Current and upcoming application of machine learning to real-life’s problems is overwhelming. Applications have enormous consequences in people’s life, and impact decisions on ...
(tests, PCA, PLS, matrix factorizations, Bayesian Networks) , unsupervised learning and machine learning methods (regression models or ranking models, online algorithms, deep networks, GAN ...) Our aim will be to provide new feasible algorithms to promote fairness by adding constraints. Finally, ...
Ensuring that machine learning (ML) models are safe, effective, and equitable across all patient groups is essential for clinical decision-making and for preventing the reinforcement of existing health disparities. This review examines notions of fairness used in ML for health, including a review of...