相关论文: BriarPatches: Pixel-Space Interventions for Induci…

Linear models are widely used in high-stakes decision-making due to their simplicity and interpretability. Yet when fairness constraints such as demographic parity are introduced, their effects on model coefficients, and thus on how…

The goal of this paper is to discover a set of discriminative patches which can serve as a fully unsupervised mid-level visual representation. The desired patches need to satisfy two requirements: 1) to be representative, they need to occur…

Natural language processing models tend to learn and encode social biases present in the data. One popular approach for addressing such biases is to eliminate encoded information from the model's representations. However, current methods…

We present a novel means of describing local image appearances using binary strings. Binary descriptors have drawn increasing interest in recent years due to their speed and low memory footprint. A known shortcoming of these representations…

Recently, there has been a lot of interest in ensuring algorithmic fairness in machine learning where the central question is how to prevent sensitive information (e.g. knowledge about the ethnic group of an individual) from adding "unfair"…

Deep learning models achieve high predictive performance but lack intrinsic interpretability, hindering our understanding of the learned prediction behavior. Existing local explainability methods focus on associations, neglecting the causal…

Mitigating bias in machine learning models is a critical endeavor for ensuring fairness and equity. In this paper, we propose a novel approach to address bias by leveraging pixel image attributions to identify and regularize regions of…

To mitigate the effects of undesired biases in models, several approaches propose to pre-process the input dataset to reduce the risks of discrimination by preventing the inference of sensitive attributes. Unfortunately, most of these…

Ensuring fairness in machine learning models is critical, particularly in high-stakes domains where biased decisions can lead to serious societal consequences. Existing preprocessing approaches generally lack transparent mechanisms for…

There is a growing interest in developing strong biomedical vision-language models. A popular approach to achieve robust representations is to use web-scale scientific data. However, current biomedical vision-language pretraining typically…

We know from prior work that LLMs encode social biases, and that this manifests in clinical tasks. In this work we adopt tools from mechanistic interpretability to unveil sociodemographic representations and biases within LLMs in the…

This paper examines the limitations of advanced text-to-image models in accurately rendering unconventional concepts which are scarcely represented or absent in their training datasets. We identify how these limitations not only confine the…

Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to transform data into a compressed binary representation independent of sensitive attributes. We…

Sensitive attributes are legally protected characteristics that should not be used to discriminate. Careful steps have been taken to minimize the risk of human bias regarding these fields, such as race and age. Large language models (LLMs)…

The success of deep neural nets heavily relies on their ability to encode complex relations between their input and their output. While this property serves to fit the training data well, it also obscures the mechanism that drives…

In image classification, a significant problem arises from bias in the datasets. When it contains only specific types of images, the classifier begins to rely on shortcuts - simplistic and erroneous rules for decision-making. This leads to…

Superpixels have become very popular in many computer vision applications. Nevertheless, they remain underexploited since the superpixel decomposition may produce irregular and non stable segmentation results due to the dependency to the…

eXplainable Artificial Intelligence (XAI) is a sub-field of Artificial Intelligence (AI) that is at the forefront of AI research. In XAI, feature attribution methods produce explanations in the form of feature importance. People often use…

Machine learning models often inherit biases from historical data, raising critical concerns about fairness and accountability. Conventional fairness interventions typically require access to sensitive attributes like gender or race, but…

In medical image diagnosis, fairness has become increasingly crucial. Without bias mitigation, deploying unfair AI would harm the interests of the underprivileged population and potentially tear society apart. Recent research addresses…