English
Related papers

Related papers: Evaluating Trade-offs in Computer Vision Between A…

200 papers

Many sets of ethics principles for responsible AI have been proposed to allay concerns about misuse and abuse of AI/ML systems. The underlying aspects of such sets of principles include privacy, accuracy, fairness, robustness,…

Computers and Society · Computer Science 2024-09-09 Conrad Sanderson , David Douglas , Qinghua Lu

Machine learning models are often personalized with categorical attributes that are protected, sensitive, self-reported, or costly to acquire. In this work, we show models that are personalized with group attributes can reduce performance…

Machine Learning · Statistics 2023-07-25 Vinith M. Suriyakumar , Marzyeh Ghassemi , Berk Ustun

Group fairness, a class of fairness notions that measure how different groups of individuals are treated differently according to their protected attributes, has been shown to conflict with one another, often with a necessary cost in loss…

Machine Learning · Computer Science 2020-07-08 Joon Sik Kim , Jiahao Chen , Ameet Talwalkar

Machine learning tasks may admit multiple competing models that achieve similar performance yet produce conflicting outputs for individual samples -- a phenomenon known as predictive multiplicity. We demonstrate that fairness interventions…

Machine Learning · Computer Science 2023-06-19 Carol Xuan Long , Hsiang Hsu , Wael Alghamdi , Flavio P. Calmon

The possible risk that AI systems could promote discrimination by reproducing and enforcing unwanted bias in data has been broadly discussed in research and society. Many current legal standards demand to remove sensitive attributes from…

Artificial Intelligence · Computer Science 2020-09-15 Boris Ruf , Marcin Detyniecki

Consider a pair of random variables $(X,Y)$ distributed according to a given joint distribution $p_{XY}$. A curator wishes to maximally disclose information about $Y$, while limiting the information leakage incurred on $X$. Adopting mutual…

Information Theory · Computer Science 2023-01-30 Borzoo Rassouli , Deniz Gündüz

This study investigates the trade-offs between fairness, privacy, and utility in image classification using machine learning (ML). Recent research suggests that generalization techniques can improve the balance between privacy and utility.…

Machine Learning · Computer Science 2024-12-17 Ahmad Hassanpour , Amir Zarei , Khawla Mallat , Anderson Santana de Oliveira , Bian Yang

Group fairness and privacy are fundamental aspects in designing trustworthy machine learning models. Previous research has highlighted conflicts between group fairness and different privacy notions. We are the first to demonstrate the…

Machine Learning · Computer Science 2024-03-06 Jan Aalmoes , Vasisht Duddu , Antoine Boutet

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…

Machine Learning · Computer Science 2020-11-02 Yuzi He , Keith Burghardt , Siyi Guo , Kristina Lerman

Fairness emerged as an important requirement to guarantee that Machine Learning (ML) predictive systems do not discriminate against specific individuals or entire sub-populations, in particular, minorities. Given the inherent subjectivity…

Machine Learning · Computer Science 2022-06-08 Karima Makhlouf , Sami Zhioua , Catuscia Palamidessi

The objective of machine learning is to extract useful information from data, while privacy is preserved by concealing information. Thus it seems hard to reconcile these competing interests. However, they frequently must be balanced when…

Machine Learning · Computer Science 2014-12-25 Zhanglong Ji , Zachary C. Lipton , Charles Elkan

Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…

Machine Learning · Statistics 2019-11-11 Mario Diaz , Peter Kairouz , Jiachun Liao , Lalitha Sankar

Irrespective of the specific definition of fairness in a machine learning application, pruning the underlying model affects it. We investigate and document the emergence and exacerbation of undesirable per-class performance imbalances,…

Computer Vision and Pattern Recognition · Computer Science 2020-09-22 Michela Paganini

As machine learning algorithms have been widely deployed across applications, many concerns have been raised over the fairness of their predictions, especially in high stakes settings (such as facial recognition and medical imaging). To…

Machine Learning · Computer Science 2021-02-16 Valeriia Cherepanova , Vedant Nanda , Micah Goldblum , John P. Dickerson , Tom Goldstein

Strategic learning studies how decision rules interact with agents who may strategically change their inputs/features to achieve better outcomes. In standard settings, models assume that the decision-maker's sole scope is to learn a…

Computer Science and Game Theory · Computer Science 2025-10-23 Valia Efthymiou , Ekaterina Fedorova , Chara Podimata

In this paper, we investigate tradeoffs among differential privacy (DP) and several important voting axioms: Pareto efficiency, SD-efficiency, PC-efficiency, Condorcet consistency, and Condorcet loser criterion. We provide upper and lower…

Computer Science and Game Theory · Computer Science 2023-07-17 Zhechen Li , Ao Liu , Lirong Xia , Yongzhi Cao , Hanpin Wang

Real-world applications of machine learning tools in high-stakes domains are often regulated to be fair, in the sense that the predicted target should satisfy some quantitative notion of parity with respect to a protected attribute.…

Machine Learning · Computer Science 2022-02-07 Han Zhao , Geoffrey J. Gordon

We propose a control-theoretic interpretation of recommender systems and use this perspective to analyze how fairness interventions shape long-term system behavior. Fairness concerns arise for both users and creators, ranging from opinion…

Systems and Control · Electrical Eng. & Systems 2026-05-05 Giulia De Pasquale , Sarah Dean , Paolo Frasca

Algorithm designers increasingly optimize not only for accuracy, but also for the fairness of the algorithm across pre-defined groups. We study the tradeoff between fairness and accuracy for any given set of inputs to the algorithm. We…

Theoretical Economics · Economics 2024-05-10 Annie Liang , Jay Lu , Xiaosheng Mu , Kyohei Okumura

Machine learning algorithms are now frequently used in sensitive contexts that substantially affect the course of human lives, such as credit lending or criminal justice. This is driven by the idea that `objective' machines base their…

Machine Learning · Computer Science 2019-01-17 Songül Tolan