This article provides a comprehensive overview of the fairness issues in artificial intelligence
(AI) systems, delving into its background, definition, and development process. The article …

Abstract Most Graph Neural Networks (GNNs) predict the labels of unseen graphs by
learning the correlation between the input graphs and labels. However, by presenting a …

Image classification models tend to make decisions based on peripheral attributes of data
items that have strong correlation with a target variable (ie, dataset bias). These biased …

Deep neural networks often make decisions based on the spurious correlations inherent in
the dataset, failing to generalize in an unbiased data distribution. Although previous …

Neural networks are prone to be biased towards spurious correlations between classes and
latent attributes exhibited in a major portion of training data, which ruins their generalization …

Empirical risk minimization (ERM) is sensitive to spurious correlations present in training
data, which poses a significant risk when deploying systems trained under this paradigm in …

Federated Learning (FL) is an increasingly popular form of distributed machine learning that
addresses privacy concerns by allowing participants to collaboratively train machine …

The performance of deep neural networks is strongly influenced by the training dataset
setup. In particular, when attributes having a strong correlation with the target attribute are …

In image classification, debiasing aims to train a classifier to be less susceptible to dataset
bias, the strong correlation between peripheral attributes of data samples and a target class …

An image is usually described by more than one attribute like" shape" and" color". When a
dataset is biased, ie, most samples have attributes spuriously correlated with the target …