paper-with-me

홈 › Papers

10 Years of Fair Representations: Challenges and Opportunities

2024-07-04 · Mattia Cerrato, Marius Köppel, Philipp Wolf, Stefan Kramer

Fair Representation Learning (FRL) is a broad set of techniques, mostly based on neural networks, that seeks to learn new representations of data in which sensitive or undesired information has been removed. Methodologically, FRL was pioneered by Richard Zemel et al. about ten years ago. The basic concepts, objectives and evaluation strategies for FRL methodologies remain unchanged to this day. In this paper, we look back at the first ten years of FRL by i) revisiting its theoretical standing in light of recent work in deep learning theory that shows the hardness of removing information in neural network representations and ii) presenting the results of a massive experimentation (225.000 model fits and 110.000 AutoML fits) we conducted with the objective of improving on the common evaluation scenario for FRL. More specifically, we use automated machine learning (AutoML) to adversarially "mine" sensitive information from supposedly fair representations. Our theoretical and experimental analysis suggests that deterministic, unquantized FRL methodologies have serious issues in removing sensitive information, which is especially troubling as they might seem "fair" at first glance.

📄 PDF Abstract BibTeX arXiv:2407.03834

Code (0)

등록된 구현이 없습니다.

Tasks

Aspect Sentiment Triplet ExtractionAutoMLLearning TheoryRepresentation Learning

Methods 이 논문이 사용한 방법론

Simple Methods For Canon Printer is Offline Fix Error 설명 없음
SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Towards Fairness-Aware Multi-Objective Optimization

2022-07-22 · Guo Yu, Lianbo Ma, Wei Du, Wenli Du 외

Recent years have seen the rapid development of fairness-aware machine learning in mitigating unfairness or discrimination in decision-making in a wide range of applications. However, much less attention has been paid to…

BIG-bench Machine LearningDecision MakingFairnessMultiobjective Optimization

Online Fair Division: A Survey

2019-11-21 · Martin Aleksandrov, Toby Walsh

We survey a burgeoning and promising new research area that considers the online nature of many practical fair division problems. We identify wide variety of such online fair division problems, as well as discuss new mec…

Survey

Bias, Fairness, and Accountability with AI and ML Algorithms

2021-05-13 · Nengfeng Zhou, Zach Zhang, Vijayan N. Nair, Harsh Singhal 외

The advent of AI and ML algorithms has led to opportunities as well as challenges. In this paper, we provide an overview of bias and fairness issues that arise with the use of ML algorithms. We describe the types and sou…

Fairness

What is Fair? Defining Fairness in Machine Learning for Health

2024-06-13 · Jianhui Gao, Benson Chou, Zachary R. McCaw, Hilary Thurston 외

Ensuring that machine learning (ML) models are safe, effective, and equitable across all patients is critical for clinical decision-making and for preventing the amplification of existing health disparities. In this work…

Decision MakingFairnessMortality Prediction

Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits

2022-05-13 · Wesley Hanwen Deng, Manish Nagireddy, Michelle Seng Ah Lee, Jatinder Singh 외

Recent years have seen the development of many open-source ML fairness toolkits aimed at helping ML practitioners assess and address unfairness in their systems. However, there has been little research investigating how …

BIG-bench Machine LearningFairness