When Machine Learning technologies are used in contexts that affect citizens, companies as
well as researchers need to be confident that there will not be any unexpected social …

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 …

Data-centric AI is at the center of a fundamental shift in software engineering where machine
learning becomes the new software, powered by big data and computing infrastructure …

Fine-tuning pretrained language models (LMs) without making any architectural changes
has become a norm for learning various language downstream tasks. However, for non …

Training ML models which are fair across different demographic groups is of critical
importance due to the increased integration of ML in crucial decision-making scenarios such …

Machine learning models are becoming pervasive in high-stakes applications. Despite their
clear benefits in terms of performance, the models could show discrimination against …

Fairness and robustness are critical elements of Trustworthy AI that need to be addressed
together. Fairness is about learning an unbiased model while robustness is about learning …

Most of existing work on fairness assumes available demographic information in the training
set. In practice, due to legal or privacy concerns, when demographic information is not …

Pairwise learning strategies are prevalent for optimizing recommendation models on implicit
feedback data, which usually learns user preference by discriminating between positive (ie …

Recently, lots of algorithms have been proposed for learning a fair classifier from
decentralized data. However, many theoretical and algorithmic questions remain open. First …