English
Related papers

Related papers: Optimising Equal Opportunity Fairness in Model Tra…

200 papers

Today, AI is increasingly being used in many high-stakes decision-making applications in which fairness is an important concern. Already, there are many examples of AI being biased and making questionable and unfair decisions. The AI…

Artificial Intelligence · Computer Science 2020-02-06 Yunfeng Zhang , Rachel K. E. Bellamy , Kush R. Varshney

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…

Machine Learning · Computer Science 2022-12-15 Prasanna Sattigeri , Soumya Ghosh , Inkit Padhi , Pierre Dognin , Kush R. Varshney

Fine-tuning pre-trained models is a widely employed technique in numerous real-world applications. However, fine-tuning these models on new tasks can lead to unfair outcomes. This is due to the absence of generalization guarantees for…

Machine Learning · Computer Science 2024-03-04 Yixuan Zhang , Feng Zhou

We investigate the prominent class of fair representation learning methods for bias mitigation. Using causal reasoning to define and formalise different sources of dataset bias, we reveal important implicit assumptions inherent to these…

Machine Learning · Computer Science 2025-02-11 Charles Jones , Fabio de Sousa Ribeiro , Mélanie Roschewitz , Daniel C. Castro , Ben Glocker

Machine learning has significantly enhanced the abilities of robots, enabling them to perform a wide range of tasks in human environments and adapt to our uncertain real world. Recent works in various machine learning domains have…

Artificial Intelligence has the capacity to amplify and perpetuate societal biases and presents profound ethical implications for society. Gender bias has been identified in the context of employment advertising and recruitment tools, due…

Computation and Language · Computer Science 2020-05-19 Susan Leavy , Gerardine Meaney , Karen Wade , Derek Greene

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…

Machine Learning · Statistics 2026-02-10 Enze Shi , Pankaj Bhagwat , Zhixian Yang , Linglong Kong , Bei Jiang

Artificial Intelligence has the potential to exacerbate societal bias and set back decades of advances in equal rights and civil liberty. Data used to train machine learning algorithms may capture social injustices, inequality or…

Computers and Society · Computer Science 2020-08-18 Susan Leavy , Barry O'Sullivan , Eugenia Siapera

Fairness,the impartial treatment towards individuals or groups regardless of their inherent or acquired characteristics [20], is a critical challenge for the successful implementation of Artificial Intelligence (AI) in multiple fields like…

Neural and Evolutionary Computing · Computer Science 2025-05-19 Catalina M Jaramillo , Paul Squires , Julian Togelius

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…

Machine Learning · Computer Science 2025-04-01 Yucong Dai , Gen Li , Feng Luo , Xiaolong Ma , Yongkai Wu

Despite being responsible for state-of-the-art results in several computer vision and natural language processing tasks, neural networks have faced harsh criticism due to some of their current shortcomings. One of them is that neural…

The performance of algorithmic decision rules is largely dependent on the quality of training datasets available to them. Biases in these datasets can raise economic and ethical concerns due to the resulting algorithms' disparate treatment…

Machine Learning · Computer Science 2025-04-14 Yifan Yang , Yang Liu , Parinaz Naghizadeh

Many internet applications are powered by machine learned models, which are usually trained on labeled datasets obtained through either implicit / explicit user feedback signals or human judgments. Since societal biases may be present in…

Machine Learning · Computer Science 2020-08-18 Sriram Vasudevan , Krishnaram Kenthapadi

Software built on top of machine learning algorithms is becoming increasingly prevalent in a variety of fields, including college admissions, healthcare, insurance, and justice. The effectiveness and efficiency of these systems heavily…

Machine Learning · Computer Science 2023-05-25 Ying Xiao , Shangwen Wang , Sicen Liu , Dingyuan Xue , Xian Zhan , Yepang Liu

Data and algorithms have the potential to produce and perpetuate discrimination and disparate treatment. As such, significant effort has been invested in developing approaches to defining, detecting, and eliminating unfair outcomes in…

Machine Learning · Computer Science 2025-02-07 Alexander Asemota , Giles Hooker

In this paper, we deal with bias mitigation techniques that remove specific data points from the training set to aim for a fair representation of the population in that set. Machine learning models are trained on these pre-processed…

Machine Learning · Computer Science 2024-09-24 Manh Khoi Duong , Stefan Conrad

Learning data representations that are transferable and are fair with respect to certain protected attributes is crucial to reducing unfair decisions while preserving the utility of the data. We propose an information-theoretically…

Machine Learning · Computer Science 2020-03-17 Jiaming Song , Pratyusha Kalluri , Aditya Grover , Shengjia Zhao , Stefano Ermon

Societal biases are reflected in large pre-trained language models and their fine-tuned versions on downstream tasks. Common in-processing bias mitigation approaches, such as adversarial training and mutual information removal, introduce…

Machine Learning · Computer Science 2023-06-06 Lukas Hauzenberger , Shahed Masoudian , Deepak Kumar , Markus Schedl , Navid Rekabsaz

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…

Computer Vision and Pattern Recognition · Computer Science 2019-03-15 Kaylee Burns , Lisa Anne Hendricks , Kate Saenko , Trevor Darrell , Anna Rohrbach

Although large language models (LLMs) have demonstrated their effectiveness in a wide range of applications, they have also been observed to perpetuate unwanted biases present in the training data, potentially leading to harm for…

Computation and Language · Computer Science 2026-03-09 Schrasing Tong , Eliott Zemour , Jessica Lu , Rawisara Lohanimit , Lalana Kagal