Related papers: Provable Detection of Propagating Sampling Bias in…

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate…

Bias can be introduced in diverse ways in machine learning datasets, for example via selection or label bias. Although these bias types in themselves have an influence on important aspects of fair machine learning, their different impact…

Machine learning currently plays an increasingly important role in people's lives in areas such as credit scoring, auto-driving, disease diagnosing, and insurance quoting. However, in many of these areas, machine learning models have…

In this work we study the problem of measuring the fairness of a machine learning model under noisy information. Focusing on group fairness metrics, we investigate the particular but common situation when the evaluation requires controlling…

Deep learning is increasingly being used in high-stake decision making applications that affect individual lives. However, deep learning models might exhibit algorithmic discrimination behaviors with respect to protected groups, potentially…

Learning under one-sided feedback (i.e., where we only observe the labels for examples we predicted positively on) is a fundamental problem in machine learning -- applications include lending and recommendation systems. Despite this, there…

A dangerous assumption that can be made from prior work on the bias transfer hypothesis (BTH) is that biases do not transfer from pre-trained large language models (LLMs) to adapted models. We invalidate this assumption by studying the BTH…

It is well known that the usefulness of a machine learning model is due to its ability to generalize to unseen data. This study uses three popular cyberbullying datasets to explore the effects of data, how it's collected, and how it's…

Datasets often contain biases which unfairly disadvantage certain groups, and classifiers trained on such datasets can inherit these biases. In this paper, we provide a mathematical formulation of how this bias can arise. We do so by…

The empirical risk minimization approach to data-driven decision making requires access to training data drawn under the same conditions as those that will be faced when the decision rule is deployed. However, in a number of settings, we…

Causal approaches to fairness have seen substantial recent interest, both from the machine learning community and from wider parties interested in ethical prediction algorithms. In no small part, this has been due to the fact that causal…

It is now well understood that machine learning models, trained on data without due care, often exhibit unfair and discriminatory behavior against certain populations. Traditional algorithmic fairness research has mainly focused on…

Supervised learning systems are trained using historical data and, if the data was tainted by discrimination, they may unintentionally learn to discriminate against protected groups. We propose that fair learning methods, despite training…

As machine learning methods are deployed in real-world settings such as healthcare, legal systems, and social science, it is crucial to recognize how they shape social biases and stereotypes in these sensitive decision-making processes.…

Machine learning algorithms often struggle to eliminate inherent data biases, particularly those arising from unreliable labels, which poses a significant challenge in ensuring fairness. Existing fairness techniques that address label bias…

While data-driven predictive models are a strictly technological construct, they may operate within a social context in which benign engineering choices entail implicit, indirect and unexpected real-life consequences. Fairness of such…

Concerns regarding fairness and bias have been raised in recent years due to the growing use of machine learning models in crucial decision-making processes, especially when it comes to delicate characteristics like gender. In order to…

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…

Ensuring fairness in transaction fraud detection models is vital due to the potential harms and legal implications of biased decision-making. Despite extensive research on algorithmic fairness, there is a notable gap in the study of bias in…

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…