中文
相关论文

相关论文: On Fairness of Medical Image Classification with M…

200 篇论文

This work proposes a novel privacy-preserving neural network feature representation to suppress the sensitive information of a learned space while maintaining the utility of the data. The new international regulation for personal data…

计算机视觉与模式识别 · 计算机科学 2020-08-10 Aythami Morales , Julian Fierrez , Ruben Vera-Rodriguez , Ruben Tolosana

Algorithmic fairness in recommender systems requires close attention to the needs of a diverse set of stakeholders that may have competing interests. Previous work in this area has often been limited by fixed, single-objective definitions…

信息检索 · 计算机科学 2024-10-08 Amanda Aird , Elena Štefancová , Cassidy All , Amy Voida , Martin Homola , Nicholas Mattei , Robin Burke

Conditional independence (CI) constraints are critical for defining and evaluating fairness in machine learning, as well as for learning unconfounded or causal representations. Traditional methods for ensuring fairness either blindly learn…

计算机视觉与模式识别 · 计算机科学 2024-04-23 Jensen Hwa , Qingyu Zhao , Aditya Lahiri , Adnan Masood , Babak Salimi , Ehsan Adeli

Explicit and implicit bias clouds human judgement, leading to discriminatory treatment of minority groups. A fundamental goal of algorithmic fairness is to avoid the pitfalls in human judgement by learning policies that improve the overall…

机器学习 · 计算机科学 2020-11-02 Yuzi He , Keith Burghardt , Siyi Guo , Kristina Lerman

Contrastive representation learning has gained much attention due to its superior performance in learning representations from both image and sequential data. However, the learned representations could potentially lead to performance…

计算与语言 · 计算机科学 2022-11-01 Jianfeng Chi , William Shand , Yaodong Yu , Kai-Wei Chang , Han Zhao , Yuan Tian

Computer vision models have been known to encode harmful biases, leading to the potentially unfair treatment of historically marginalized groups, such as people of color. However, there remains a lack of datasets balanced along demographic…

计算机视觉与模式识别 · 计算机科学 2024-02-13 Nicholas Lui , Bryan Chia , William Berrios , Candace Ross , Douwe Kiela

In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation…

机器学习 · 统计学 2019-12-10 Eduardo Hugo Sanchez , Mathieu Serrurier , Mathias Ortner

If our models are used in new or unexpected cases, do we know if they will make fair predictions? Previously, researchers developed ways to debias a model for a single problem domain. However, this is often not how models are trained and…

机器学习 · 计算机科学 2019-11-18 Candice Schumann , Xuezhi Wang , Alex Beutel , Jilin Chen , Hai Qian , Ed H. Chi

Representation learning algorithms offer the opportunity to learn invariant representations of the input data with regard to nuisance factors. Many authors have leveraged such strategies to learn fair representations, i.e., vectors where…

机器学习 · 计算机科学 2025-07-16 Mattia Cerrato , Marius Köppel , Roberto Esposito , Stefan Kramer

Arbitrary, inconsistent, or faulty decision-making raises serious concerns, and preventing unfair models is an increasingly important challenge in Machine Learning. Data often reflect past discriminatory behavior, and models trained on such…

机器学习 · 计算机科学 2023-06-29 I. Oliveira e Silva , C. Soares , I. Sousa , R. Ghani

The use of machine learning (ML) in high-stakes societal decisions has encouraged the consideration of fairness throughout the ML lifecycle. Although data integration is one of the primary steps to generate high quality training data, most…

机器学习 · 计算机科学 2022-04-01 Sainyam Galhotra , Karthikeyan Shanmugam , Prasanna Sattigeri , Kush R. Varshney

Gender is one of the most common attributes used to describe an individual. It is used in multiple domains such as human computer interaction, marketing, security, and demographic reports. Research has been performed to automate the task of…

计算机视觉与模式识别 · 计算机科学 2018-05-22 Maneet Singh , Shruti Nagpal , Richa Singh , Mayank Vatsa

We develop a novel method for ensuring fairness in machine learning which we term as the Renyi Fair Information Bottleneck (RFIB). We consider two different fairness constraints - demographic parity and equalized odds - for learning fair…

机器学习 · 计算机科学 2022-05-03 Adam Gronowski , William Paul , Fady Alajaji , Bahman Gharesifard , Philippe Burlina

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…

机器学习 · 计算机科学 2025-02-07 Alexander Asemota , Giles Hooker

In this paper, we propose FairNN a neural network that performs joint feature representation and classification for fairness-aware learning. Our approach optimizes a multi-objective loss function in which (a) learns a fair representation by…

Data collected in the real world often encapsulates historical discrimination against disadvantaged groups and individuals. Existing fair machine learning (FairML) research has predominantly focused on mitigating discriminative bias in the…

机器学习 · 计算机科学 2024-06-19 Zhining Liu , Ruizhong Qiu , Zhichen Zeng , Yada Zhu , Hendrik Hamann , Hanghang Tong

Representation learning, and interpreting learned representations, are key areas of focus in machine learning and neuroscience. Both fields generally use representations as a means to understand or improve a system's computations. In this…

机器学习 · 计算机科学 2024-09-24 Andrew Kyle Lampinen , Stephanie C. Y. Chan , Katherine Hermann

Despite the astonishing performance of deep-learning based approaches for visual tasks such as semantic segmentation, they are known to produce miscalibrated predictions, which could be harmful for critical decision-making processes.…

图像与视频处理 · 电气工程与系统科学 2021-05-25 Agostina J. Larrazabal , César Martínez , Jose Dolz , Enzo Ferrante

Fair machine learning is receiving an increasing attention in machine learning fields. Researchers in fair learning have developed correlation or association-based measures such as demographic disparity, mistreatment disparity, calibration,…

计算机与社会 · 计算机科学 2019-11-20 Wen Huang , Yongkai Wu , Lu Zhang , Xintao Wu

The issue of group fairness in machine learning models, where certain sub-populations or groups are favored over others, has been recognized for some time. While many mitigation strategies have been proposed in centralized learning, many of…

机器学习 · 计算机科学 2023-05-18 Ganghua Wang , Ali Payani , Myungjin Lee , Ramana Kompella
‹ 上一页 1 8 9 10 下一页 ›