Algorithmic Bias

Algorithmic bias refers to systematic and repeatable errors in computer systems that create unfair outcomes, often disadvantaging certain demographic groups. Current research focuses on identifying and mitigating these biases across various machine learning models, including those used in healthcare, hiring, and social media, with a particular emphasis on understanding how data characteristics and model architectures contribute to unfairness. This is a critical area of investigation because biased algorithms can perpetuate and amplify existing societal inequalities, demanding the development of fairer and more equitable AI systems.

Papers

April 28, 2024

A Note on Asynchronous Challenges: Unveiling Formulaic Bias and Data Loss in the Hayashi-Yoshida Estimator
Evangelos Georgiadis
Short Note Algorithmic Bias Linear Estimator Intrinsic Bias Asynchronous Learning Publication Bias Poisson Process Novel Estimator Data Loss

April 24, 2024

Debiasing Machine Unlearning with Counterfactual Examples
Ziheng Chen, Jia Wang, Jun Zhuang, Abbavaram Gowtham Reddy, Fabrizio Silvestri, Jin Huang, Kaushiki Nag, Kun Kuang, Xin Ning, Gabriele Tolomei
Unlearning Framework Algorithmic Bias Counterfactual Example Length Bias Data Bias

April 18, 2024

Neural Networks with Causal Graph Constraints: A New Approach for Treatment Effects Estimation
Roger Pros, Jordi Vitrià
Neural Network Causal Graph Novel Approach Treatment Effect Algorithmic Bias Causal Constraint

April 11, 2024

Laissez-Faire Harms: Algorithmic Biases in Generative Language Models
Evan Shieh, Faye-Marie Vassel, Cassidy Sugimoto, Thema Monroe-White
Generative Model Absolute Stance Bias Generative Language Model Social Bias Stereotype Content Algorithmic Bias Fair Credit Prompt Model

April 3, 2024

Auditing the Use of Language Models to Guide Hiring Decisions
Johann D. Gaebler, Sharad Goel, Aziz Huq, Prasanna Tambe
Large Language Model Language Model Absolute Stance Bias Greater Public Use Decision Relevant Information Algorithmic Bias Algorithm Auditing

March 21, 2024

Debiasing surgeon: fantastic weights and how to find them
Rémi Nahon, Ivan Luiz De Moura Matos, Van-Tam Nguyen, Enzo Tartaglione
Balancing Weight Algorithmic Bias Debiasing Method Fair Model

February 23, 2024

Debiasing Machine Learning Models by Using Weakly Supervised Learning
Renan D. B. Brotto, Jean-Michel Loubes, Laurent Risser, Jean-Pierre Florens, Kenji Nose-Filho, João M. T. Romano
Bias Mitigation Sensitive Data Weakly Supervised Learning Algorithmic Bias Model Debiasing

January 22, 2024

Differentiable Tree Search in Latent State Space
Dixant Mittal, Wee Sun Lee
World Model State Space Algorithmic Bias Graph Expansion

December 23, 2023

Mitigating Algorithmic Bias on Facial Expression Recognition
Glauco Amigo, Pablo Rivas Perea, Robert J. Marks
Absolute Stance Bias Facial Expression Recognition Expression Recognition Algorithmic Bias Biased Datasets Biased Data

December 9, 2023

Mitigating Nonlinear Algorithmic Bias in Binary Classification
Wendy Hui, Wai Kwong Lau
Causal Model Bias Mitigation Binary Classification Algorithmic Bias Demographic Bias

December 5, 2023

Detecting algorithmic bias in medical-AI models using trees
Jeffrey Smith, Andre Holder, Rishikesan Kamaleswaran, Yao Xie
Tree Specie AI Model Algorithmic Bias Decision Support System Clinical Decision Support System

October 30, 2023

Unmasking Bias in AI: A Systematic Review of Bias Detection and Mitigation Strategies in Electronic Health Record-based Models
Feng Chen, Liqin Wang, Julie Hong, Jiaqi Jiang, Li Zhou
Artificial Intelligence Electronic Health Record Systematic Review Bias Evaluation Algorithmic Bias Health Disparity BIAS Detection

October 19, 2023

Detecting and Mitigating Algorithmic Bias in Binary Classification using Causal Modeling
Wendy Hui, Wai Kwong Lau
Data Detection Gender Bias Causal Model Bias Mitigation Binary Classification Algorithmic Bias

September 27, 2023

Potential Ways to Detect Unfairness in HRI and to Re-establish Positive Group Dynamics
Astrid Rosenthal-von der Pütten, Stefan Schiffer
Robot Behavior New Way Algorithmic Bias VAM HRI Interface

September 4, 2023

Measuring, Interpreting, and Improving Fairness of Algorithms using Causal Inference and Randomized Experiments
James Enouen, Tianshu Sun, Yan Liu
Practical Algorithm Procedural Fairness Causal Inference Algorithmic Bias Measurement System Algorithmic Decision Fair Algorithm Randomized Experiment

August 10, 2023

Benchmarking Algorithmic Bias in Face Recognition: An Experimental Approach Using Synthetic Faces and Human Evaluation
Hao Liang, Pietro Perona, Guha Balakrishnan
Face Recognition Human Evaluation Synthetic Face Algorithmic Bias Perceptual Similarity Face Generator Experimental Approach

August 1, 2023

Fair Models in Credit: Intersectional Discrimination and the Amplification of Inequity
Savina Kim, Stefan Lessmann, Galina Andreeva, Michael Rovatsos
Algorithmic Bias Fair Model Fairness Assessment Intersectional Social Attribute Consumer Credit

July 31, 2023

No Fair Lunch: A Causal Perspective on Dataset Bias in Machine Learning for Medical Imaging
Charles Jones, Daniel C. Castro, Fabio De Sousa Ribeiro, Ozan Oktay, Melissa McCradden, Ben Glocker
Machine Learning Medical Imaging Algorithmic Bias Causal Analysis Dataset Bias

July 18, 2023

Mitigating Label Bias via Decoupled Confident Learning
Yunyi Li, Maria De-Arteaga, Maytal Saar-Tsechansky
Algorithmic Bias Feature Decoupling Label Bias Bias Label Human Generated Label

July 6, 2023

The Role of Subgroup Separability in Group-Fair Medical Image Classification
Charles Jones, Mélanie Roschewitz, Ben Glocker
Integral Role Algorithmic Bias Deep Learning Classification Performance Disparity Subgroup Performance