Most existing works on fairness assume the model has full access to demographic
information. However, there exist scenarios where demographic information is partially …

Achieving fairness across diverse clients in Federated Learning (FL) remains a significant
challenge due to the heterogeneity of the data and the inaccessibility of sensitive attributes …

The past decade has observed a great advancement in AI with deep learning-based models
being deployed in diverse scenarios including safety-critical applications. As these AI …

While much of the rapidly growing literature on fair decision-making focuses on metrics for
one-shot decisions, recent work has raised the intriguing possibility of designing sequential …

Developing fair and unbiased models is important for good scientific practice and clinical
utility. This paper delves into the specific biases associated with artificial intelligence (AI) in …

Developing fair and unbiased models is important for good scientific practice and clinical
utility. This paper delves into the specific biases associated with artificial intelligence (AI) in …

The issue of bias in Machine Learning (ML) models is a significant challenge for the
machine learning community. Real-world biases can be embedded in the data used to train …