Fairness Property

Fairness in machine learning aims to ensure that algorithms treat individuals equitably, avoiding discriminatory outcomes based on sensitive attributes like race or gender. Current research focuses on developing methods to certify and quantify fairness, particularly within deep neural networks and graph convolutional networks, employing techniques like symbolic interval analysis, label flipping, and fairness-aware optimization algorithms. This work is crucial for mitigating bias in high-stakes applications such as loan applications, hiring processes, and criminal justice, promoting accountability and trust in AI systems.

Papers

September 5, 2024

FairQuant: Certifying and Quantifying Fairness of Deep Neural Networks
Brian Hyeongseok Kim, Jingbo Wang, Chao Wang
Deep Neural Network Individual Fairness Fairness Property Fairness Datasets

March 11, 2024

Monotone Individual Fairness
Yahav Bechavod
Individual Fairness Online Classification Fairness Property Oracle Efficient Algorithm Fairness Problem

February 19, 2024

FairProof : Confidential and Certifiable Fairness for Neural Networks
Chhavi Yadav, Amrita Roy Chowdhury, Dan Boneh, Kamalika Chaudhuri
Neural Network Procedural Fairness Zero Knowledge Fairness Property Fairness Certification

January 26, 2024

FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently
Zicun Cong, Shi Baoxu, Shan Li, Jaewon Yang, Qi He, Jian Pei
Model Fairness Graph Convolutional Neural Network Fairness Property Unbiased Segmentation Fair Training

May 29, 2023

The Leximin Approach for a Sequence of Collective Decisions
Ido Kahana, Noam Hazon
Sequence of Sequence Fairness Notion Welfare Maximization Fairness Property Collective Decision Approximate Leximin

February 11, 2023

Fair Enough: Standardizing Evaluation and Model Selection for Fairness Research in NLP
Xudong Han, Timothy Baldwin, Trevor Cohn
Procedural Fairness NLP Field Model Selection Fairness Research Fair Learning Fairness Property

January 23, 2023

Accelerating Fair Federated Learning: Adaptive Federated Adam
Li Ju, Tianru Zhang, Salman Toor, Andreas Hellander
FAIR Federated Learning Fairness Property Adaptive Federated Learning

December 20, 2022

Human-Guided Fair Classification for Natural Language Processing
Florian E. Dorner, Momchil Peychev, Nikola Konstantinov, Naman Goel, Elliott Ash, Martin Vechev
Natural Language Processing Text Classifier Fair Classification Fairness Property Candidate Set

December 8, 2022

Fairify: Fairness Verification of Neural Networks
Sumon Biswas, Hridesh Rajan
Neural Network Fairness Property Fairness Certification Fairness Verification

December 4, 2022

Fairness in Contextual Resource Allocation Systems: Metrics and Incompatibility Results
Nathanael Jo, Bill Tang, Kathryn Dullerud, Sina Aghaei, Eric Rice, Phebe Vayanos
Procedural Fairness Resource Allocation Metric Library Fairness Metric Self Compatibility Fairness Property Allocation Policy

November 11, 2022

Identifying, measuring, and mitigating individual unfairness for supervised learning models and application to credit risk models
Rasoul Shahsavarifar, Jithu Chandran, Mario Inchiosa, Amit Deshpande, Mario Schlener, Vishal Gossain, Yara Elias, Vinaya Murali
Application Proficiency Supervised Learning Group Fairness Individual Fairness Fairness Property Fairness Mitigation Credit Risk Model

September 15, 2022

iFlipper: Label Flipping for Individual Fairness
Hantian Zhang, Ki Hyun Tae, Jaeyoung Park, Xu Chu, Steven Euijong Whang
Procedural Fairness Individual Fairness Fairness Property Label Flipping

July 20, 2022

Measuring and signing fairness as performance under multiple stakeholder distributions
David Lopez-Paz, Diane Bouchacourt, Levent Sagun, Nicolas Usunier
Procedural Fairness System Performance Fairness Metric Biased Prediction Multi Stakeholder Fairness Property Fairness Certification

May 20, 2022