Related papers: Resampled Datasets Are Not Enough: Mitigating Soci…

Assessing the diversity of a dataset of information associated with people is crucial before using such data for downstream applications. For a given dataset, this often involves computing the imbalance or disparity in the empirical…

Deep neural networks trained via empirical risk minimisation often exhibit significant performance disparities across groups, particularly when group and task labels are spuriously correlated (e.g., "grassy background" and "cows"). Existing…

Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased…

Image captioning models are known to perpetuate and amplify harmful societal bias in the training set. In this work, we aim to mitigate such gender bias in image captioning models. While prior work has addressed this problem by forcing…

Image-to-image reconstruction problems with free or inexpensive metadata in the form of class labels appear often in biological and medical image domains. Existing text-guided or style-transfer image-to-image approaches do not translate to…

Learning generalized models from biased data is an important undertaking toward fairness in deep learning. To address this issue, recent studies attempt to identify and leverage bias-conflicting samples free from spurious correlations…

Ensuring a neural network is not relying on protected attributes (e.g., race, sex, age) for predictions is crucial in advancing fair and trustworthy AI. While several promising methods for removing attribute bias in neural networks have…

Large language models (LLMs) acquire general linguistic knowledge from massive-scale pretraining. However, pretraining data mainly comprised of web-crawled texts contain undesirable social biases which can be perpetuated or even amplified…

Text-to-image diffusion models have been adopted into key commercial workflows, such as art generation and image editing. Characterising the implicit social biases they exhibit, such as gender and racial stereotypes, is a necessary first…

With the recent proliferation of the use of text classifications, researchers have found that there are certain unintended biases in text classification datasets. For example, texts containing some demographic identity-terms (e.g., "gay",…

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…

As the social impact of visual recognition has been under scrutiny, several protected-attribute balanced datasets emerged to address dataset bias in imbalanced datasets. However, in facial attribute classification, dataset bias stems from…

Recent advances in text-to-image diffusion models have enabled the generation of diverse and high-quality images. While impressive, the images often fall short of depicting subtle details and are susceptible to errors due to ambiguity in…

Existing machine learning models have proven to fail when it comes to their performance for minority groups, mainly due to biases in data. In particular, datasets, especially social data, are often not representative of minorities. In this…

In today's society, AI systems are increasingly used to make critical decisions such as credit scoring and patient triage. However, great convenience brought by AI systems comes with troubling prevalence of bias against underrepresented…

Models trained on real-world data often mirror and exacerbate existing social biases. Traditional methods for mitigating these biases typically require prior knowledge of the specific biases to be addressed, such as gender or racial biases,…

The measurement of bias in machine learning often focuses on model performance across identity subgroups (such as man and woman) with respect to groundtruth labels. However, these methods do not directly measure the associations that a…

As text-to-image systems continue to grow in popularity with the general public, questions have arisen about bias and diversity in the generated images. Here, we investigate properties of images generated in response to prompts which are…

Subject selection plays a critical role in experimental studies, especially ones with human subjects. Anecdotal evidence suggests that many such studies, done at or near university campus settings suffer from selection bias, i.e., the…

For a machine learning model to generalize effectively to unseen data within a particular problem domain, it is well-understood that the data needs to be of sufficient size and representative of real-world scenarios. Nonetheless, real-world…