Related papers: Accounting for Model Uncertainty in Algorithmic Di…

Recent research reveals that machine learning (ML) models are highly sensitive to minor changes in their training procedure, such as the inclusion or exclusion of a single data point, leading to conflicting predictions on individual data…

As machine learning systems are increasingly used to make real world legal and financial decisions, it is of paramount importance that we develop algorithms to verify that these systems do not discriminate against minorities. We design a…

Empirical investigations into unintended model behavior often show that the algorithm is predicting another outcome than what was intended. These exposes highlight the need to identify when algorithms predict unintended quantities - ideally…

With model trustworthiness being crucial for sensitive real-world applications, practitioners are putting more and more focus on improving the uncertainty calibration of deep neural networks. Calibration errors are designed to quantify the…

Algorithmic decision-making systems are increasingly used throughout the public and private sectors to make important decisions or assist humans in making these decisions with real social consequences. While there has been substantial…

Deep neural networks (DNNs) have made significant progress, but often suffer from fairness issues, as deep models typically show distinct accuracy differences among certain subgroups (e.g., males and females). Existing research addresses…

Machine learning risks reinforcing biases present in data and, as we argue in this work, in what is absent from data. In healthcare, societal and decision biases shape patterns in missing data, yet the algorithmic fairness implications of…

Computers are increasingly used to make decisions that have significant impact in people's lives. Often, these predictions can affect different population subgroups disproportionately. As a result, the issue of fairness has received much…

Algorithmic decision-making in societal contexts, such as retail pricing, loan administration, recommendations on online platforms, etc., can be framed as stochastic optimization under bandit feedback, which typically requires…

We study fairness in collaborative-filtering recommender systems, which are sensitive to discrimination that exists in historical data. Biased data can lead collaborative filtering methods to make unfair predictions against minority groups…

People are rated and ranked, towards algorithmic decision making in an increasing number of applications, typically based on machine learning. Research on how to incorporate fairness into such tasks has prevalently pursued the paradigm of…

Fairness in algorithmic decision-making processes is attracting increasing concern. When an algorithm is applied to human-related decision-making an estimator solely optimizing its predictive power can learn biases on the existing data,…

Data and algorithms have the potential to produce and perpetuate discrimination and disparate treatment. As such, significant effort has been invested in developing approaches to defining, detecting, and eliminating unfair outcomes in…

Deep learning crime predictive tools use past crime data and additional behavioral datasets to forecast future crimes. Nevertheless, these tools have been shown to suffer from unfair predictions across minority racial and ethnic groups.…

Algorithms learned from data are increasingly used for deciding many aspects in our life: from movies we see, to prices we pay, or medicine we get. Yet there is growing evidence that decision making by inappropriately trained algorithms may…

Training datasets for machine learning often have some form of missingness. For example, to learn a model for deciding whom to give a loan, the available training data includes individuals who were given a loan in the past, but not those…

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…

In credit markets, screening algorithms aim to discriminate between good-type and bad-type borrowers. However, when doing so, they can also discriminate between individuals sharing a protected attribute (e.g. gender, age, racial origin) and…

Developing classification algorithms that are fair with respect to sensitive attributes of the data has become an important problem due to the growing deployment of classification algorithms in various social contexts. Several recent works…

The use of algorithmic (learning-based) decision making in scenarios that affect human lives has motivated a number of recent studies to investigate such decision making systems for potential unfairness, such as discrimination against…