ML Fairness

Machine learning (ML) fairness research aims to mitigate biases in algorithms and datasets that lead to discriminatory outcomes for certain demographic groups. Current research focuses on developing methods for detecting and mitigating bias in various data modalities (text, images, time series), including techniques like data augmentation and label noise correction, and exploring the use of zero-knowledge proofs to verify fairness in deployed models. This field is crucial for ensuring equitable application of ML across diverse populations and for building trust in AI systems, impacting both the ethical development of AI and its practical deployment in sensitive areas like healthcare and criminal justice.

Papers

September 17, 2024

OATH: Efficient and Flexible Zero-Knowledge Proofs of End-to-End ML Fairness
Olive Franzese, Ali Shahin Shamsabadi, Hamed Haddadi
High Efficiency Zero Knowledge Fair AI ML Fairness

May 15, 2024

Small but Fair! Fairness for Multimodal Human-Human and Robot-Human Mental Wellbeing Coaching
Jiaee Cheong, Micol Spitale, Hatice Gunes
Procedural Fairness Affective Computing Fairness Aware Machine ML Fairness Robot Health

March 21, 2024

Navigating Fairness: Practitioners' Understanding, Challenges, and Strategies in AI/ML Development
Aastha Pant, Rashina Hoda, Chakkrit Tantithamthavorn, Burak Turhan
Machine Learning Artificial Intelligence Technical Challenge General Strategy Fair AI AI Practitioner ML Fairness

September 7, 2023

TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Models
Emmanuel Klu, Sameer Sethi
Language Model Classification Code Text Datasets Model Debiasing ML Fairness

June 28, 2023

Systematic analysis of the impact of label noise correction on ML Fairness
I. Oliveira e Silva, C. Soares, I. Sousa, R. Ghani
Global Impact Biased Datasets Bias Label ML Fairness NoIsy Label CorrEction

May 16, 2023

Consensus and Subjectivity of Skin Tone Annotation for ML Fairness
Candice Schumann, Gbolahan O. Olanubi, Auriel Wright, Ellis Monk, Courtney Heldreth, Susanna Ricco
Consensus Group Decision Subjective Knowledge ML Fairness Attribute Feature Skin Tone Annotation

April 8, 2023

Connecting Fairness in Machine Learning with Public Health Equity
Shaina Raza
Machine Learning Procedural Fairness Fair Machine Learning Systematic Bias ML Fairness Health Equity Equitable Framework

January 18, 2023

Synthcity: facilitating innovative use cases of synthetic data in different data modalities
Zhaozhi Qian, Bogdan-Constantin Cebere, Mihaela van der Schaar
Synthetic Data Data Modality ML Fairness Real World Use Case

October 24, 2022

Simultaneous Improvement of ML Model Fairness and Performance by Identifying Bias in Data
Bhushan Chaudhari, Akash Agarwal, Tanmoy Bhowmik
Machine Learning Model Raw Data System Performance Absolute Stance Bias Bias Mitigation Model Accuracy Potential Bias ML Fairness Simultaneous Improvement

June 2, 2022

Improving Fairness in Large-Scale Object Recognition by CrowdSourced Demographic Information
Zu Kim, André Araujo, Bingyi Cao, Cam Askew, Jack Sim, Mike Green, N'Mah Fodiatu Yilla, Tobias Weyand
Object Recognition Landmark Detection Fairness Improvement Relevance Score Crowd Sourced Data ML Fairness

May 13, 2022

Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
Wesley Hanwen Deng, Manish Nagireddy, Michelle Seng Ah Lee, Jatinder Singh, Zhiwei Steven Wu, Kenneth Holstein, Haiyi Zhu
Machine Learning Practitioner ML Fairness Fairness Toolkits

May 6, 2022

Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches
Lindsay Weinberg
AI Fairness Interdisciplinary Perspective Fairness Intervention Lower Critique Accuracy ML Fairness Rethinking Fairness

January 17, 2022

Visual Identification of Problematic Bias in Large Label Spaces
Alex Bäuerle, Aybuke Gul Turker, Ken Burke, Osman Aka, Timo Ropinski, Christina Greer, Mani Varadarajan
Ground Truth Fair Machine Learning Label Space Fairness Assessment ML Fairness

ML Fairness

Papers

OATH: Efficient and Flexible Zero-Knowledge Proofs of End-to-End ML Fairness

Small but Fair! Fairness for Multimodal Human-Human and Robot-Human Mental Wellbeing Coaching

Navigating Fairness: Practitioners' Understanding, Challenges, and Strategies in AI/ML Development

TIDE: Textual Identity Detection for Evaluating and Augmenting Classification and Language Models

Systematic analysis of the impact of label noise correction on ML Fairness

Consensus and Subjectivity of Skin Tone Annotation for ML Fairness

Connecting Fairness in Machine Learning with Public Health Equity

Synthcity: facilitating innovative use cases of synthetic data in different data modalities

Simultaneous Improvement of ML Model Fairness and Performance by Identifying Bias in Data

Improving Fairness in Large-Scale Object Recognition by CrowdSourced Demographic Information

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

Rethinking Fairness: An Interdisciplinary Survey of Critiques of Hegemonic ML Fairness Approaches

Visual Identification of Problematic Bias in Large Label Spaces