Bias mitigation for machine learning classifiers: A comprehensive survey
This article provides a comprehensive survey of bias mitigation methods for achieving
fairness in Machine Learning (ML) models. We collect a total of 341 publications concerning …
fairness in Machine Learning (ML) models. We collect a total of 341 publications concerning …
A comprehensive survey of forgetting in deep learning beyond continual learning
Forgetting refers to the loss or deterioration of previously acquired information or knowledge.
While the existing surveys on forgetting have primarily focused on continual learning …
While the existing surveys on forgetting have primarily focused on continual learning …
Incorporating symmetry into deep dynamics models for improved generalization
Recent work has shown deep learning can accelerate the prediction of physical dynamics
relative to numerical solvers. However, limited physical accuracy and an inability to …
relative to numerical solvers. However, limited physical accuracy and an inability to …
FIND: human-in-the-loop debugging deep text classifiers
Since obtaining a perfect training dataset (ie, a dataset which is considerably large,
unbiased, and well-representative of unseen cases) is hardly possible, many real-world text …
unbiased, and well-representative of unseen cases) is hardly possible, many real-world text …
Controllable guarantees for fair outcomes via contrastive information estimation
Controlling bias in training datasets is vital for ensuring equal treatment, or parity, between
different groups in downstream applications. A naive solution is to transform the data so that …
different groups in downstream applications. A naive solution is to transform the data so that …
Deep learning on a healthy data diet: Finding important examples for fairness
Data-driven predictive solutions predominant in commercial applications tend to suffer from
biases and stereotypes, which raises equity concerns. Prediction models may discover, use …
biases and stereotypes, which raises equity concerns. Prediction models may discover, use …
Fair normalizing flows
Fair representation learning is an attractive approach that promises fairness of downstream
predictors by encoding sensitive data. Unfortunately, recent work has shown that strong …
predictors by encoding sensitive data. Unfortunately, recent work has shown that strong …
Scalable infomin learning
The task of infomin learning aims to learn a representation with high utility while being
uninformative about a specified target, with the latter achieved by minimising the mutual …
uninformative about a specified target, with the latter achieved by minimising the mutual …
Attributing fair decisions with attention interventions
The widespread use of Artificial Intelligence (AI) in consequential domains, such as
healthcare and parole decision-making systems, has drawn intense scrutiny on the fairness …
healthcare and parole decision-making systems, has drawn intense scrutiny on the fairness …
Disentangled information bottleneck
The information bottleneck (IB) method is a technique for extracting information that is
relevant for predicting the target random variable from the source random variable, which is …
relevant for predicting the target random variable from the source random variable, which is …