Related papers: VB-Mitigator: An Open-source Framework for Evaluat…
The growing capability and accessibility of machine learning has led to its application to many real-world domains and data about people. Despite the benefits algorithmic systems may bring, models can reflect, inject, or exacerbate implicit…
In recent years, vision-language models have made significant strides, excelling in tasks like optical character recognition and geometric problem-solving. However, several critical issues remain: 1) Proprietary models often lack…
One of the difficulties of artificial intelligence is to ensure that model decisions are fair and free of bias. In research, datasets, metrics, techniques, and tools are applied to detect and mitigate algorithmic unfairness and bias. This…
Ensuring fairness in image classification prevents models from perpetuating and amplifying bias. Concept bottleneck models (CBMs) map images to high-level, human-interpretable concepts before making predictions via a sparse, one-layer…
Vision-Language (V-L) pre-trained models such as CLIP show prominent capabilities in various downstream tasks. Despite this promise, V-L models are notoriously limited by their inherent social biases. A typical demonstration is that V-L…
As machine learning (ML) systems become increasingly widespread, it is necessary to audit these systems for biases prior to their deployment. Recent research has developed algorithms for effectively identifying intersectional bias in the…
There are several bias mitigators that can reduce algorithmic bias in machine learning models but, unfortunately, the effect of mitigators on fairness is often not stable when measured across different data splits. A popular approach to…
Machine Learning models have been deployed across many different aspects of society, often in situations that affect social welfare. Although these models offer streamlined solutions to large problems, they may contain biases and treat…
Fairness is a critical requirement for Machine Learning (ML) software, driving the development of numerous bias mitigation methods. Previous research has identified a leveling-down effect in bias mitigation for computer vision and natural…
Software bias is an increasingly important operational concern for software engineers. We present a large-scale, comprehensive empirical study of 17 representative bias mitigation methods for Machine Learning (ML) classifiers, evaluated…
Mitigating bias in automated decision-making systems, particularly in deep learning models, is a critical challenge due to nuanced definitions of fairness, dataset-specific biases, and the inherent trade-off between fairness and accuracy.…
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…
The widespread use of machine learning and data-driven algorithms for decision making has been steadily increasing over many years. \emph{Bias} in the data can adversely affect this decision-making. We present a new mitigation strategy to…
We present VB, a benchmark that tests whether vision-language models can determine what is and is not visible in a photograph, and abstain when a human viewer cannot reliably answer. Each item pairs a single photo with a short yes/no…
This paper provides a comprehensive survey of bias mitigation methods for achieving fairness in Machine Learning (ML) models. We collect a total of 341 publications concerning bias mitigation for ML classifiers. These methods can be…
Addressing biases in computer vision models is crucial for real-world AI deployments. However, mitigating visual biases is challenging due to their unexplainable nature, often identified indirectly through visualization or sample…
A multitude of work has shown that machine learning-based medical diagnosis systems can be biased against certain subgroups of people. This has motivated a growing number of bias mitigation algorithms that aim to address fairness issues in…
While the need for well-trained, fair ML systems is increasing ever more, measuring fairness for modern models and datasets is becoming increasingly difficult as they grow at an unprecedented pace. One key challenge in scaling common…
Over the past 15 years, hundreds of bias mitigation methods have been proposed in the pursuit of fairness in machine learning (ML). However, algorithmic biases are domain-, task-, and model-specific, leading to a `portability trap': bias…
Machine learning systems are increasingly deployed in high-stakes domains, yet they remain vulnerable to bias systematic disparities that disproportionately impact specific demographic groups. Traditional bias detection methods often depend…