Related papers: Subgroups Matter for Robust Bias Mitigation
Efforts to mitigate bias and enhance fairness in the artificial intelligence (AI) community have predominantly focused on technical solutions. While numerous reviews have addressed bias in AI, this review uniquely focuses on the practical…
To measure bias, we encourage teams to consider using AUC Gap: the absolute difference between the highest and lowest test AUC for subgroups (e.g., gender, race, SES, prior knowledge). It is agnostic to the AI/ML algorithm used and it…
The use of machine learning to guide clinical decision making has the potential to worsen existing health disparities. Several recent works frame the problem as that of algorithmic fairness, a framework that has attracted considerable…
Machine learning practitioners frequently observe tension between predictive accuracy and group fairness constraints -- yet sometimes fairness interventions appear to improve accuracy. We show that both phenomena can be artifacts of…
In recent times, there have been increasing accusations on artificial intelligence systems and algorithms of computer vision of possessing implicit biases. Even though these conversations are more prevalent now and systems are improving by…
We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is…
The remarkable performance of deep learning models and their applications in consequential domains (e.g., facial recognition) introduces important challenges at the intersection of equity and security. Fairness and robustness are two…
Algorithmic fairness is frequently motivated in terms of a trade-off in which overall performance is decreased so as to improve performance on disadvantaged groups where the algorithm would otherwise be less accurate. Contrary to this, we…
The evaluation of supervised machine learning models is a critical stage in the development of reliable predictive systems. Despite the widespread availability of machine learning libraries and automated workflows, model assessment is often…
It is evident that deep text classification models trained on human data could be biased. In particular, they produce biased outcomes for texts that explicitly include identity terms of certain demographic groups. We refer to this type of…
Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity…
Machine learning best practice statements have proliferated, but there is a lack of consensus on what the standards should be. For fairness standards in particular, there is little guidance on how fairness might be achieved in practice.…
Over the past two decades, the notion of implicit bias has come to serve as an important component in our understanding of discrimination in activities such as hiring, promotion, and school admissions. Research on implicit bias posits that…
Traditional approaches to ensure group fairness in algorithmic decision making aim to equalize ``total'' error rates for different subgroups in the population. In contrast, we argue that the fairness approaches should instead focus only on…
Research on fairness in machine learning has been recently extended to recommender systems. One of the factors that may impact fairness is bias disparity, the degree to which a group's preferences on various item categories fail to be…
The idealization of a static machine-learned model, trained once and deployed forever, is not practical. As input distributions change over time, the model will not only lose accuracy, any constraints to reduce bias against a protected…
In fairness audits, a standard objective is to detect whether a given algorithm performs substantially differently between subgroups. Properly powering the statistical analysis of such audits is crucial for obtaining informative fairness…
Machine learning methods have achieved good performance and been widely applied in various real-world applications. They can learn the model adaptively and be better fit for special requirements of different tasks. Generally, a good machine…
Machine learning models are updated as new data is acquired or new architectures are developed. These updates usually increase model performance, but may introduce backward compatibility errors, where individual users or groups of users see…
Datasets can be biased due to societal inequities, human biases, under-representation of minorities, etc. Our goal is to certify that models produced by a learning algorithm are pointwise-robust to potential dataset biases. This is a…