Related papers: Deep Learning on a Healthy Data Diet: Finding Impo…

Modern NLP systems exhibit a range of biases, which a growing literature on model debiasing attempts to correct. However current progress is hampered by a plurality of definitions of bias, means of quantification, and oftentimes vague…

Deep learning crime predictive tools use past crime data and additional behavioral datasets to forecast future crimes. Nevertheless, these tools have been shown to suffer from unfair predictions across minority racial and ethnic groups.…

Cyberbullying is a widespread adverse phenomenon among online social interactions in today's digital society. While numerous computational studies focus on enhancing the cyberbullying detection performance of machine learning algorithms,…

Biases in existing datasets used to train algorithmic decision rules can raise ethical and economic concerns due to the resulting disparate treatment of different groups. We propose an algorithm for sequentially debiasing such datasets…

Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in…

Over the last few years, Contextualized Pre-trained Neural Language Models, such as BERT, GPT, have shown significant gains in various NLP tasks. To enhance the robustness of existing pre-trained models, one way is adversarial examples…

There is a broad consensus on the importance of deep learning models in tasks involving complex data. Often, an adequate understanding of these models is required when focusing on the transparency of decisions in human-critical…

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in…

Counterfactual fairness is an approach to AI fairness that tries to make decisions based on the outcomes that an individual with some kind of sensitive status would have had without this status. This paper proposes Double Machine Learning…

Biases in culture, gender, ethnicity, etc. have existed for decades and have affected many areas of human social interaction. These biases have been shown to impact machine learning (ML) models, and for natural language processing (NLP),…

Deep learning models for semantics are generally evaluated using naturalistic corpora. Adversarial methods, in which models are evaluated on new examples with known semantic properties, have begun to reveal that good performance at these…

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.…

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…

Machine Learning systems are increasingly prevalent across healthcare, law enforcement, and finance but often operate on historical data, which may carry biases against certain demographic groups. Causal and counterfactual fairness provides…

In consequential decision-making applications, mitigating unwanted biases in machine learning models that yield systematic disadvantage to members of groups delineated by sensitive attributes such as race and gender is one key intervention…

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…

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous…

The class imbalance problem can cause machine learning models to produce an undesirable performance on the minority class as well as the whole dataset. Using data augmentation techniques to increase the number of samples is one way to…

Decision making in crucial applications such as lending, hiring, and college admissions has witnessed increasing use of algorithmic models and techniques as a result of a confluence of factors such as ubiquitous connectivity, ability to…

Most machine learning methods are known to capture and exploit biases of the training data. While some biases are beneficial for learning, others are harmful. Specifically, image captioning models tend to exaggerate biases present in…