Fairness Perception

Fairness perception in AI focuses on understanding and mitigating biases in algorithms' decisions and their impact on different user groups. Current research emphasizes developing methods to detect and correct biases, often employing techniques like optimal transport, Bayesian approaches, and adversarial training within various model architectures, including deep learning and graph neural networks. This work is crucial for building trustworthy AI systems, addressing ethical concerns, and ensuring equitable outcomes across diverse populations in applications ranging from healthcare and criminal justice to social media moderation and recommender systems. A key challenge lies in achieving fairness generalization across different datasets and contexts, and in understanding how explanations of AI decisions influence fairness perceptions and human reliance on AI recommendations.

Papers

October 4, 2024

Understanding Decision Subjects' Engagement with and Perceived Fairness of AI Models When Opportunities of Qualification Improvement Exist
Meric Altug Gemalmaz, Ming Yin
Procedural Fairness Emerging Opportunity Artificial Intelligence Model AI Model Fair Decision Fairness Perception

October 3, 2024

Overcoming Representation Bias in Fairness-Aware data Repair using Optimal Transport
Abigail Langbridge, Anthony Quinn, Robert Shorten
Optimal Transport Target Distribution Fairness Perception

September 11, 2024

Dynamic Fairness Perceptions in Human-Robot Interaction
Houston Claure, Kate Candon, Inyoung Shin, Marynel Vázquez
Human Robot Interaction Fairness Aware Fairness Perception Dynamic Fairness

May 28, 2024

Hate Speech Detection with Generalizable Target-aware Fairness
Tong Chen, Danny Wang, Xurong Liang, Marten Risius, Gianluca Demartini, Hongzhi Yin
Hate Speech Detection Fairness Perception Semantic Affinity Aware Filter Fairness Preference

May 22, 2024

Perceptual Fairness in Image Restoration
Guy Ohayon, Michael Elad, Tomer Michaeli
Image Restoration Image Restoration Task Face Super Resolution Fairness Perception Perceptual Grouping

April 4, 2024

An ExplainableFair Framework for Prediction of Substance Use Disorder Treatment Completion
Mary M. Lucas, Xiaoyang Wang, Chia-Hsuan Chang, Christopher C. Yang, Jacqueline E. Braughton, Quyen M. Ngo
Human Prediction High Explainability Model Bias Explainable Model Fairness Improvement Fairness Perception Substance Use Disorder

February 27, 2024

Preserving Fairness Generalization in Deepfake Detection
Li Lin, Xinan He, Yan Ju, Xin Wang, Feng Ding, Shu Hu
Deepfake Detection Deep Fake Fairness Perception Fairness Learning Cross Domain Fraud Detection

October 12, 2023

The Impact of Explanations on Fairness in Human-AI Decision-Making: Protected vs Proxy Features
Navita Goyal, Connor Baumler, Tin Nguyen, Hal Daumé
Global Impact Procedural Fairness Line by Line Explanation Model Bias Model Fairness Fair Decision Fairness Perception Human AI Decision Making Weapon of Mass Destruction Proxy

October 8, 2023

FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
Raman Dutt, Ondrej Bohdal, Sotirios A. Tsaftaris, Timothy Hospedales
Procedural Fairness Parameter Efficient Fine Tuning Medical Image Analysis Generalization Gap Fairness Perception Fair Learning Fairness Learning

August 28, 2023

Fair Few-shot Learning with Auxiliary Sets
Song Wang, Jing Ma, Lu Cheng, Jundong Li
Shot Learning Fairness Aware Fairness Perception Fairness Performance Fairness Optimization Auxiliary Item Relationship

August 22, 2023

May 16, 2023

Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluation
Bjørnar Vassøy, Helge Langseth
Global Evaluation Recommender System NCD Method Comprehensive Survey Fairness Metric Fairness Perception Seller Side Outcome Fairness

April 7, 2023

Assessing Perceived Fairness from Machine Learning Developer's Perspective
Anoop Mishra, Deepak Khazanchi
Machine Learning Visual Perspective Fair Machine Learning Fairness Perception

December 7, 2022

Fairness and Explainability: Bridging the Gap Towards Fair Model Explanations
Yuying Zhao, Yu Wang, Tyler Derr
Procedural Fairness High Explainability Fairness Perception

November 25, 2022

Interpreting Unfairness in Graph Neural Networks via Training Node Attribution
Yushun Dong, Song Wang, Jing Ma, Ninghao Liu, Jundong Li
Graph Neural Network Fairness Perception Biased Prediction Training Data Attribution Influence Estimation Fair GNN

September 23, 2022

Explanations, Fairness, and Appropriate Reliance in Human-AI Decision-Making
Jakob Schoeffer, Maria De-Arteaga, Niklas Kuehl
Procedural Fairness Line by Line Explanation Fairness Objective Fairness Perception Human AI Decision Making Feature Explanation Using Contrasting Concept

September 21, 2022

Fairness Reprogramming
Guanhua Zhang, Yihua Zhang, Yang Zhang, Wenqi Fan, Qing Li, Sijia Liu, Shiyu Chang
Fairness Perception Fairness Criterion

August 17, 2022

Towards Generating Robust, Fair, and Emotion-Aware Explanations for Recommender Systems
Bingbing Wen, Yunhe Feng, Yongfeng Zhang, Chirag Shah
Recommender System Explanation Generation Explainable Recommendation Fairness Perception Emotion Distribution

May 6, 2022

The Road to Explainability is Paved with Bias: Measuring the Fairness of Explanations
Aparna Balagopalan, Haoran Zhang, Kimia Hamidieh, Thomas Hartvigsen, Frank Rudzicz, Marzyeh Ghassemi
Procedural Fairness Line by Line Explanation High Explainability Absolute Stance Bias Explainability Method Built Road Explanation Model Fairness Perception