4.1 Review

Exploring gender biases in ML and AI academic research through systematic literature review

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Surgery

Use of artificial intelligence for gender bias analysis in letters of recommendation for general surgery residency candidates

Daniel Sarraf et al.

Summary: Gender bias and linguistic differences were detected in letters of recommendation written for surgical residency applicants, with more gendered wording found in female letters and more positive sentiment in male letters.

AMERICAN JOURNAL OF SURGERY (2021)

Article Computer Science, Theory & Methods

A Survey on Bias and Fairness in Machine Learning

Ninareh Mehrabi et al.

Summary: With the widespread use of AI systems in everyday life, fairness in design has become crucial. Researchers have developed methods to address biases in different subdomains and established a taxonomy for fairness definitions. Existing work shows biases in AI applications, and researchers are working on solutions to mitigate these problems.

ACM COMPUTING SURVEYS (2021)

Article Computer Science, Hardware & Architecture

WinoGrande: An Adversarial Winograd Schema Challenge at Scale

Keisuke Sakaguchi et al.

Summary: Through the WinoGrande dataset and a comparison of human and machine performance in commonsense reasoning, the study found that state-of-the-art models have lower accuracy in solving commonsense challenges, confirming that the high performance on the original WSC was inflated by spurious biases in the dataset.

COMMUNICATIONS OF THE ACM (2021)

Article Computer Science, Artificial Intelligence

SensitiveNets: Learning Agnostic Representations with Application to Face Images

Aythami Morales et al.

Summary: This work proposes a novel privacy-preserving neural network feature representation to suppress sensitive information while maintaining the utility of data. The approach ensures privacy and equality of opportunity by enforcing privacy of selected attributes. Fairness improvement is a result of this privacy-preserving learning method rather than the direct objective.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Article Computer Science, Information Systems

Investigating gender fairness of recommendation algorithms in the music domain

Alessandro B. Melchiorre et al.

Summary: Research has shown that recommender systems may perform differently between user groups with various demographic characteristics, leading to unfairness. By introducing a concept of fairness and evaluating different collaborative filtering algorithms, the study aims to investigate the fairness of recommendation results towards specific gender groups. Significant discrepancies in performance between male and female user groups have been observed, and a resampling strategy has shown slight improvements in fairness measures without compromising accuracy.

INFORMATION PROCESSING & MANAGEMENT (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Gender Bias and Under-Representation in Natural Language Processing Across Human Languages

Yan Chen et al.

Summary: This paper reports and analyzes measurements of gender bias in the Wikipedia corpora for nine languages, revealing crucial gaps in the NLP-pipeline and the systematic under-representation of the majority of human voices in shaping our collective future through NLP-guided decisions.

AIES '21: PROCEEDINGS OF THE 2021 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY (2021)

Proceedings Paper Computer Science, Artificial Intelligence

What's Fair about Individual Fairness?

Will Fleisher

Summary: Individual fairness, based on the intuitive principle of similar treatment, is considered by some as the correct definition of algorithmic fairness. However, it has limitations such as inability to guarantee fairness, risk of encoding bias, requiring prior moral judgments, and facing incommensurability of relevant values. Therefore, individual fairness should be viewed as just one tool among several for mitigating algorithmic bias.

AIES '21: PROCEEDINGS OF THE 2021 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Detecting Emergent Intersectional Biases: Contextualized Word Embeddings Contain a Distribution of Human-like Biases

Wei Guo et al.

Summary: This study examines biases in English static word embeddings and explores social and intersectional biases in neural language models as well as how to measure them in context. The findings indicate varying degrees of bias across different models, with intersectional biases and emergent intersectional biases significantly impacting algorithm performance within specific groups.

AIES '21: PROCEEDINGS OF THE 2021 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY (2021)

Article Computer Science, Information Systems

DENOUNCER: Detection of Unfairness in Classifiers

Jinyang Li et al.

Summary: The use of automated data-driven tools for decision-making has become popular, but it has also led to an increase in reported cases of algorithmic bias and discrimination, prompting extensive research on algorithmic fairness. Various notions of fairness have been proposed, but detecting groups that are treated unfairly by algorithms may be computationally prohibitive.

PROCEEDINGS OF THE VLDB ENDOWMENT (2021)

Proceedings Paper Computer Science, Artificial Intelligence

Federated Adversarial Debiasing for Fair and Transferable Representations

Junyuan Hong et al.

Summary: Federated learning is a distributed learning framework that faces challenges from user heterogeneity, which may lead to biased models. FADE is a novel approach that addresses bias without requiring sensitive user information, allowing users to opt-out from adversarial components for privacy or computational concerns.

KDD '21: PROCEEDINGS OF THE 27TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING (2021)

Article Computer Science, Artificial Intelligence

Gender Bias in Machine Translation

Beatrice Savoldi et al.

Summary: This paper critically reviews gender bias in machine translation, summarizes previous analyses and proposed mitigating strategies, and advocates for future research to move towards a unified framework.

TRANSACTIONS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (2021)

Proceedings Paper Computer Science, Artificial Intelligence

User Bias in Beyond-Accuracy Measurement of Recommendation Algorithms

Ningxia Wang et al.

Summary: The study analyzed user biases in recommendation algorithms using a large-scale survey dataset, identifying factors that may contribute to these biases. By examining user behavior patterns and algorithm performance, potential problematic biases and their causes were analyzed.

15TH ACM CONFERENCE ON RECOMMENDER SYSTEMS (RECSYS 2021) (2021)

Proceedings Paper Automation & Control Systems

Digital Enterprise Technologies: Do Enterprise Control and Automation Technologies Reinforce Gender Biases and Marginalisation?

N. Donnelly et al.

Summary: This research explores how digital automation systems reinforce gender discrimination by marginalizing and excluding genders beyond the socially constructed binary sex/gender combinations. Findings suggest that digital data systems perpetuate gender bias and contribute to social violence towards marginalized communities, impacting engineering ethics and cultural relationships. The study contributes to discussions on diversity, inclusion, and structural marginalization in science and engineering.

IFAC PAPERSONLINE (2021)

Proceedings Paper Computer Science, Artificial Intelligence

InsideBias: Measuring Bias in Deep Networks and Application to Face Gender Biometrics

Ignacio Serna et al.

Summary: This work explores biases in learning processes based on deep neural network architectures by analyzing the effects of bias on deep learning through a toy example and a gender detection case study. It proposes a novel method called Inside Bias for detecting biased models based on how they represent information rather than their performance.

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2021)

Proceedings Paper Computer Science, Theory & Methods

WhatWe Can't Measure, We Can't Understand: Challenges to Demographic Data Procurement in the Pursuit of Fairness

McKane Andrus et al.

Summary: Practitioners in the field of algorithmic fairness struggle with access to demographic data, raising complex questions about legal requirements, privacy concerns, and fairness. Challenges surrounding the procurement of demographic data must be considered collectively by businesses, regulators, researchers, and community groups to address algorithmic bias effectively.

PROCEEDINGS OF THE 2021 ACM CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY, FACCT 2021 (2021)

Article Computer Science, Artificial Intelligence

Assessing gender bias in machine translation: a case study with Google Translate

Marcelo O. R. Prates et al.

NEURAL COMPUTING & APPLICATIONS (2020)

Review Computer Science, Hardware & Architecture

A group of industry, academic, and government experts convene in Philadelphia to explore the roots of algorithmic bias

Alexandra Chouldechova et al.

COMMUNICATIONS OF THE ACM (2020)

Article Computer Science, Information Systems

Female Librarians and Male Computer Programmers? Gender Bias in Occupational Images on Digital Media Platforms

Vivek K. Singh et al.

JOURNAL OF THE ASSOCIATION FOR INFORMATION SCIENCE AND TECHNOLOGY (2020)

Editorial Material Anesthesiology

Bias and ethical considerations in machine learning and the automation of perioperative risk assessment

Vikas N. O'Reilly-Shah et al.

BRITISH JOURNAL OF ANAESTHESIA (2020)

Proceedings Paper Computer Science, Information Systems

Do Neural Ranking Models Intensify Gender Bias?

Navid Rekabsaz et al.

PROCEEDINGS OF THE 43RD INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL (SIGIR '20) (2020)

Proceedings Paper Computer Science, Information Systems

Quantifying Gender Bias in Different Corpora

Marzieh Babaeianjelodar et al.

WWW'20: COMPANION PROCEEDINGS OF THE WEB CONFERENCE 2020 (2020)

Proceedings Paper Computer Science, Information Systems

A Unifying Framework for Fairness-Aware Influence Maximization

Golnoosh Farnadi et al.

WWW'20: COMPANION PROCEEDINGS OF THE WEB CONFERENCE 2020 (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Mitigating Bias in Algorithmic Hiring: Evaluating Claims and Practices

Manish Raghavan et al.

FAT* '20: PROCEEDINGS OF THE 2020 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Toward Situated Interventions for Algorithmic Equity: Lessons from the Field

Michael Katell et al.

FAT* '20: PROCEEDINGS OF THE 2020 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY (2020)

Proceedings Paper Computer Science, Artificial Intelligence

It's Not Just Black and White: Classifying Defendant Mugshots Based on the Multidimensionality of Race and Ethnicity

Rahul Kumar Dass et al.

2020 17TH CONFERENCE ON COMPUTER AND ROBOT VISION (CRV 2020) (2020)

Proceedings Paper Computer Science, Artificial Intelligence

Mitigating Algorithmic Bias: Evolving an Augmentation Policy that is Non-Biasing

Philip Smith et al.

2020 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW) (2020)

Review Computer Science, Information Systems

Investigating Bias in Facial Analysis Systems: A Systematic Review

Ashraf Khalil et al.

IEEE ACCESS (2020)

Article Computer Science, Theory & Methods

Hacking the Cis-tem Transgender Citizens and the Early Digital State

Marie Hicks

IEEE ANNALS OF THE HISTORY OF COMPUTING (2019)

Article Automation & Control Systems

Unintended Consequences of Biased Robotic and Artificial Intelligence Systems

Ludovic Righetti et al.

IEEE ROBOTICS & AUTOMATION MAGAZINE (2019)

Proceedings Paper Computer Science, Theory & Methods

Bias in Bios: A Case Study of Semantic Representation Bias in a High-Stakes Setting

Maria De-Arteaga et al.

FAT*'19: PROCEEDINGS OF THE 2019 CONFERENCE ON FAIRNESS, ACCOUNTABILITY, AND TRANSPARENCY (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Fairness across Network Positions in Cyberbullying Detection Algorithms

Vivek K. Singh et al.

PROCEEDINGS OF THE 2019 IEEE/ACM INTERNATIONAL CONFERENCE ON ADVANCES IN SOCIAL NETWORKS ANALYSIS AND MINING (ASONAM 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Epistemic Therapy for Bias in Automated Decision-Making

Thomas Krendl Gilbert et al.

AIES '19: PROCEEDINGS OF THE 2019 AAAI/ACM CONFERENCE ON AI, ETHICS, AND SOCIETY (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Balanced Datasets Are Not Enough: Estimating and Mitigating Gender Bias in Deep Image Representations

Tianlu Wang et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Proceedings Paper Computer Science, Information Systems

Fairness-Aware Ranking in Search & Recommendation Systems with Application to LinkedIn Talent Search

Sahin Cem Geyik et al.

KDD'19: PROCEEDINGS OF THE 25TH ACM SIGKDD INTERNATIONAL CONFERENCCE ON KNOWLEDGE DISCOVERY AND DATA MINING (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Analyzing Sentiments of German Job References

Finn Folkerts et al.

2019 IEEE INTERNATIONAL CONFERENCE ON HUMANIZED COMPUTING AND COMMUNICATION (HCC 2019) (2019)

Proceedings Paper Computer Science, Theory & Methods

Demographic Inference and Representative Population Estimates from Multilingual Social Media Data

Zijian Wang et al.

WEB CONFERENCE 2019: PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE (WWW 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Fairness-Aware Machine Learning: Practical Challenges and Lessons Learned

Sarah Bird et al.

PROCEEDINGS OF THE TWELFTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING (WSDM'19) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Exploring Automatic Face Recognition on Match Performance and Gender Bias for Children

Nisha Srinivas et al.

2019 IEEE WINTER APPLICATIONS OF COMPUTER VISION WORKSHOPS (WACVW) (2019)

Article Industrial Relations & Labor

'Bias in, Bias out': gender equality and the future of work debate

Debra Howcroft et al.

LABOUR & INDUSTRY-A JOURNAL OF THE SOCIAL AND ECONOMIC RELATIONS OF WORK (2019)

Proceedings Paper Computer Science, Cybernetics

Investigating Implicit Gender Bias and Embodiment of White Males in Virtual Reality with Full Body Visuomotor Synchrony

Sarah Lopez et al.

CHI 2019: PROCEEDINGS OF THE 2019 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (2019)

Proceedings Paper Computer Science, Theory & Methods

Algorithms for Fair Team Formation in Online Labour Marketplaces

Giorgio Barnabo et al.

COMPANION OF THE WORLD WIDE WEB CONFERENCE (WWW 2019 ) (2019)

Proceedings Paper Computer Science, Cybernetics

Guidelines for Human-AI Interaction

Saleema Amershi et al.

CHI 2019: PROCEEDINGS OF THE 2019 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS (2019)

Article Computer Science, Information Systems

Gender bias in sentiment analysis

Mike Thelwall

ONLINE INFORMATION REVIEW (2018)

News Item Computer Science, Hardware & Architecture

The Dangers of Automating Social Programs

Esther Shein

COMMUNICATIONS OF THE ACM (2018)

Editorial Material Dermatology

Automated Classification of Skin Lesions: From Pixels to Practice

Akhila Narla et al.

JOURNAL OF INVESTIGATIVE DERMATOLOGY (2018)

News Item Multidisciplinary Sciences

The bias detectives

Rachel Courtland

NATURE (2018)

Proceedings Paper Computer Science, Information Systems

Investigating User Perception of Gender Bias in Image Search

Jahna Otterbacher et al.

ACM/SIGIR PROCEEDINGS 2018 (2018)

Proceedings Paper Computer Science, Software Engineering

IEEE P7003™ Standard for Algorithmic Bias Considerations

Ansgar Koene et al.

2018 IEEE/ACM INTERNATIONAL WORKSHOP ON SOFTWARE FAIRNESS (FAIRWARE 2018) (2018)

Proceedings Paper Computer Science, Information Systems

FairTest: Discovering Unwarranted Associations in Data-Driven Applications

Florian Tramer et al.

2017 IEEE EUROPEAN SYMPOSIUM ON SECURITY AND PRIVACY (EUROS&P) (2017)