English
Related papers

Related papers: Mitigating Label Bias via Decoupled Confident Lear…

200 papers

To mitigate societal biases implicitly encoded in recent successful pretrained language models, a diverse array of approaches have been proposed to encourage model fairness, focusing on prompting, data augmentation, regularized fine-tuning,…

Computation and Language · Computer Science 2025-01-30 Jingxuan Xu , Wuyang Chen , Linyi Li , Yao Zhao , Yunchao Wei

We propose selective debiasing -- an inference-time safety mechanism designed to enhance the overall model quality in terms of prediction performance and fairness, especially in scenarios where retraining the model is impractical. The…

Computation and Language · Computer Science 2025-03-12 Gleb Kuzmin , Neemesh Yadav , Ivan Smirnov , Timothy Baldwin , Artem Shelmanov

We propose an information-theoretic bias measurement technique through a causal interpretation of spurious correlation, which is effective to identify the feature-level algorithmic bias by taking advantage of conditional mutual information.…

Machine Learning · Computer Science 2022-01-11 Seonguk Seo , Joon-Young Lee , Bohyung Han

Pre-trained language models have achieved remarkable success across diverse applications but remain susceptible to spurious, concept-driven correlations that impair robustness and fairness. In this work, we introduce CURE, a novel and…

Computation and Language · Computer Science 2025-09-11 Aysenur Kocak , Shuo Yang , Bardh Prenkaj , Gjergji Kasneci

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

Traditional approaches to learning fair machine learning models often require rebuilding models from scratch, typically without considering potentially existing models. In a context where models need to be retrained frequently, this can…

Machine Learning · Computer Science 2025-07-22 Federico Di Gennaro , Thibault Laugel , Vincent Grari , Marcin Detyniecki

While long-tailed semi-supervised learning (LTSSL) has attracted growing attention in many real-world classification tasks, existing LTSSL algorithms typically assume that labeled and unlabeled data share nearly identical class…

Machine Learning · Computer Science 2026-05-19 Kai Gan , Tong Wei , Min-Ling Zhang

Bias in computer vision systems can perpetuate or even amplify discrimination against certain populations. Considering that bias is often introduced by biased visual datasets, many recent research efforts focus on training fair models using…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Ioannis Sarridis , Christos Koutlis , Symeon Papadopoulos , Christos Diou

Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e., representation) through disentangled representation…

Machine Learning · Computer Science 2023-09-06 Jindi Zhang , Luning Wang , Dan Su , Yongxiang Huang , Caleb Chen Cao , Lei Chen

Increasingly, software is making autonomous decisions in case of criminal sentencing, approving credit cards, hiring employees, and so on. Some of these decisions show bias and adversely affect certain social groups (e.g. those defined by…

Machine Learning · Computer Science 2021-07-12 Joymallya Chakraborty , Suvodeep Majumder , Tim Menzies

Learning with noisy labels aims to ensure model generalization given a label-corrupted training set. The sample selection strategy achieves promising performance by selecting a label-reliable subset for model training. In this paper, we…

Machine Learning · Computer Science 2025-04-11 Qi Wei , Lei Feng , Haobo Wang , Bo An

Research has shown that, machine learning models might inherit and propagate undesired social biases encoded in the data. To address this problem, fair training algorithms are developed. However, most algorithms assume we know…

Machine Learning · Computer Science 2022-04-12 Mustafa Safa Ozdayi , Murat Kantarcioglu , Rishabh Iyer

Mitigating biases in machine learning models has become an increasing concern in Natural Language Processing (NLP), particularly in developing fair text embeddings, which are crucial yet challenging for real-world applications like search…

Computation and Language · Computer Science 2024-06-25 Wenlong Deng , Blair Chen , Beidi Zhao , Chiyu Zhang , Xiaoxiao Li , Christos Thrampoulidis

Contrastive learning (CL) has achieved astonishing progress in computer vision, speech, and natural language processing fields recently with self-supervised learning. However, CL approach to the supervised setting is not fully explored,…

Computation and Language · Computer Science 2022-05-23 Zhenyu Zhang , Yuming Zhao , Meng Chen , Xiaodong He

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

Machine Learning · Computer Science 2025-03-25 Jiali Cheng , Hadi Amiri

Fairness is a core element in the trustworthy deployment of deepfake detection models, especially in the field of digital identity security. Biases in detection models toward different demographic groups, such as gender and race, may lead…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Feng Ding , Wenhui Yi , Yunpeng Zhou , Xinan He , Hong Rao , Shu Hu

To reduce human error and prejudice, many high-stakes decisions have been turned over to machine algorithms. However, recent research suggests that this does not remove discrimination, and can perpetuate harmful stereotypes. While…

Computers and Society · Computer Science 2019-12-18 Yuzi He , Keith Burghardt , Kristina Lerman

This paper strives to address image classifier bias, with a focus on both feature and label embedding spaces. Previous works have shown that spurious correlations from protected attributes, such as age, gender, or skin tone, can cause…

Computer Vision and Pattern Recognition · Computer Science 2021-10-28 William Thong , Cees G. M. Snoek

When recognizing emotions from speech, we encounter two common problems: how to optimally capture emotion-relevant information from the speech signal and how to best quantify or categorize the noisy subjective emotion labels.…

Audio and Speech Processing · Electrical Eng. & Systems 2022-11-04 Sofoklis Kakouros , Themos Stafylakis , Ladislav Mosner , Lukas Burget

It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…

Machine Learning · Computer Science 2024-12-06 Vito Paolo Pastore , Massimiliano Ciranni , Davide Marinelli , Francesca Odone , Vittorio Murino