English
Related papers

Related papers: Learning Fair Models without Sensitive Attributes:…

200 papers

The vast majority of techniques to train fair models require access to the protected attribute (e.g., race, gender), either at train time or in production. However, in many important applications this protected attribute is largely…

Machine Learning · Computer Science 2023-10-04 Hadi Elzayn , Emily Black , Patrick Vossler , Nathanael Jo , Jacob Goldin , Daniel E. Ho

While there is significant interest in using generative AI tools as general-purpose models for specific ML applications, discriminative models are much more widely deployed currently. One of the key shortcomings of these discriminative AI…

Artificial Intelligence · Computer Science 2023-12-13 Son The Nguyen , Theja Tulabandhula , Mary Beth Watson-Manheim

Fairness in visual recognition is becoming a prominent and critical topic of discussion as recognition systems are deployed at scale in the real world. Models trained from data in which target labels are correlated with protected attributes…

Computer Vision and Pattern Recognition · Computer Science 2021-04-05 Vikram V. Ramaswamy , Sunnie S. Y. Kim , Olga Russakovsky

We study fair classification in the presence of an omniscient adversary that, given an $\eta$, is allowed to choose an arbitrary $\eta$-fraction of the training samples and arbitrarily perturb their protected attributes. The motivation…

Machine Learning · Computer Science 2021-11-24 L. Elisa Celis , Anay Mehrotra , Nisheeth K. Vishnoi

Model fairness is becoming important in class-incremental learning for Trustworthy AI. While accuracy has been a central focus in class-incremental learning, fairness has been relatively understudied. However, naively using all the samples…

Machine Learning · Computer Science 2025-12-30 Jaeyoung Park , Minsu Kim , Steven Euijong Whang

Despite the success of recommender systems in alleviating information overload, fairness issues have raised concerns in recent years, potentially leading to unequal treatment for certain user groups. While efforts have been made to improve…

Information Retrieval · Computer Science 2025-05-27 Haoran Xin , Ying Sun , Chao Wang , Yanke Yu , Weijia Zhang , Hui Xiong

Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stems from an overreliance on features that are spuriously correlated with the…

Machine Learning · Computer Science 2026-01-01 Alexander C. Li , Ananya Kumar , Deepak Pathak

Feature learning forms the cornerstone for tackling challenging learning problems in domains such as speech, computer vision and natural language processing. In this paper, we consider a novel class of matrix and tensor-valued features,…

Machine Learning · Computer Science 2015-04-21 Majid Janzamin , Hanie Sedghi , Anima Anandkumar

Fairness in machine learning is more important than ever as ethical concerns continue to grow. Individual fairness demands that individuals differing only in sensitive attributes receive the same outcomes. However, commonly used machine…

Machine Learning · Computer Science 2025-08-22 Ruihan Zhang , Jun Sun

Much of the previous machine learning (ML) fairness literature assumes that protected features such as race and sex are present in the dataset, and relies upon them to mitigate fairness concerns. However, in practice factors like privacy…

Machine Learning · Computer Science 2020-11-04 Preethi Lahoti , Alex Beutel , Jilin Chen , Kang Lee , Flavien Prost , Nithum Thain , Xuezhi Wang , Ed H. Chi

Algorithmic decision making process now affects many aspects of our lives. Standard tools for machine learning, such as classification and regression, are subject to the bias in data, and thus direct application of such off-the-shelf tools…

Machine Learning · Statistics 2017-10-16 Junpei Komiyama , Hajime Shimao

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

We present a flexible framework for learning predictive models that approximately satisfy the equalized odds notion of fairness. This is achieved by introducing a general discrepancy functional that rigorously quantifies violations of this…

Machine Learning · Statistics 2020-06-09 Yaniv Romano , Stephen Bates , Emmanuel J. Candès

Human agents routinely reason on instances with incomplete and muddied data (and weigh the cost of obtaining further features). In contrast, much of ML is devoted to the unrealistic, sterile environment where all features are observed and…

Machine Learning · Computer Science 2024-10-08 Yang Li , Junier Oliva

Previous works on the fairness of toxic language classifiers compare the output of models with different identity terms as input features but do not consider the impact of other important concepts present in the context. Here, besides…

Computation and Language · Computer Science 2022-10-20 Isar Nejadgholi , Esma Balkır , Kathleen C. Fraser , Svetlana Kiritchenko

This work tackles the issue of fairness in the context of generative procedures, such as image super-resolution, which entail different definitions from the standard classification setting. Moreover, while traditional group fairness…

Machine Learning · Computer Science 2021-07-05 Ajil Jalal , Sushrut Karmalkar , Jessica Hoffmann , Alexandros G. Dimakis , Eric Price

Feature selection is a prevalent data preprocessing paradigm for various learning tasks. Due to the expensive cost of acquiring supervision information, unsupervised feature selection sparks great interests recently. However, existing…

Machine Learning · Computer Science 2021-06-07 Xiaoying Xing , Hongfu Liu , Chen Chen , Jundong Li

Assessing the fairness of a decision making system with respect to a protected class, such as gender or race, is challenging when class membership labels are unavailable. Probabilistic models for predicting the protected class based on…

Applications · Statistics 2018-11-28 Jiahao Chen , Nathan Kallus , Xiaojie Mao , Geoffry Svacha , Madeleine Udell

Training ML models which are fair across different demographic groups is of critical importance due to the increased integration of ML in crucial decision-making scenarios such as healthcare and recruitment. Federated learning has been…

Machine Learning · Computer Science 2022-11-28 Yahya H. Ezzeldin , Shen Yan , Chaoyang He , Emilio Ferrara , Salman Avestimehr

We consider the problem of deep fair clustering, which partitions data into clusters via the representations extracted by deep neural networks while hiding sensitive data attributes. To achieve fairness, existing methods present a variety…

Machine Learning · Computer Science 2024-03-26 Xiang Zhang