相关论文: Measuring Fairness in Generative Models

With the growing utilization of machine learning in healthcare, there is increasing potential to enhance healthcare outcomes. However, this also brings the risk of perpetuating biases in data and model design that can harm certain…

Several prior works have shown that language models (LMs) can generate text containing harmful social biases and stereotypes. While decoding algorithms play a central role in determining properties of LM generated text, their impact on the…

Naively trained AI models can be heavily biased. This can be particularly problematic when the biases involve legally or morally protected attributes such as ethnic background, age or gender. Existing solutions to this problem come at the…

Deep neural networks have achieved exceptional results across a range of applications. As the demand for efficient and sparse deep learning models escalates, the significance of model compression, particularly pruning, is increasingly…

Scoring systems, as a type of predictive model, have significant advantages in interpretability and transparency and facilitate quick decision-making. As such, scoring systems have been extensively used in a wide variety of industries such…

As machine learning has been deployed ubiquitously across applications in modern data science, algorithmic fairness has become a great concern. Among them, imposing fairness constraints during learning, i.e. in-processing fair training, has…

Early studies of risk assessment algorithms used in criminal justice revealed widespread racial biases. In response, machine learning researchers have developed methods for fairness, many of which rely on equalizing empirical metrics across…

The rapid trend of deploying artificial intelligence (AI) and machine learning (ML) systems in socially consequential domains has raised growing concerns about their trustworthiness, including potential discriminatory behaviours. Research…

Deep learning's unprecedented success raises several ethical concerns ranging from biased predictions to data privacy. Researchers tackle these issues by introducing fairness metrics, or federated learning, or differential privacy. A first,…

Generative models are known to be difficult to assess. Recent works, especially on generative adversarial networks (GANs), produce good visual samples of varied categories of images. However, the validation of their quality is still…

Current studies on adversarial robustness mainly focus on aggregating local robustness results from a set of data samples to evaluate and rank different models. However, the local statistics may not well represent the true global robustness…

Machine learning models have achieved widespread success but often inherit and amplify historical biases, resulting in unfair outcomes. Traditional fairness methods typically impose constraints at the prediction level, without addressing…

The rapid developments of various machine learning models and their deployments in several applications has led to discussions around the importance of looking beyond the accuracies of these models. Fairness of such models is one such…

Generative adversarial networks (GAN) are a powerful subclass of generative models. Despite a very rich research activity leading to numerous interesting GAN algorithms, it is still very hard to assess which algorithm(s) perform better than…

The FAIR Guiding Principles aim to improve the findability, accessibility, interoperability, and reusability of digital content by making them both human and machine actionable. However, these principles have not yet been broadly adopted in…

As we rely on machine learning (ML) models to make more consequential decisions, the issue of ML models perpetuating or even exacerbating undesirable historical biases (e.g., gender and racial biases) has come to the fore of the public's…

Graph neural networks (GNNs) are powerful tools for learning from graph-structured data but often produce biased predictions with respect to sensitive attributes. Fairness-aware GNNs have been actively studied for mitigating biased…

Testing machine learning software for ethical bias has become a pressing current concern. In response, recent research has proposed a plethora of new fairness metrics, for example, the dozens of fairness metrics in the IBM AIF360 toolkit.…

Over the past several years, a slew of different methods to measure the fairness of a machine learning model have been proposed. However, despite the growing number of publications and implementations, there is still a critical lack of…

Unfair behaviors of Machine Learning (ML) software have garnered increasing attention and concern among software engineers. To tackle this issue, extensive research has been dedicated to conducting fairness testing of ML software, and this…