Adversarial Debiasing

Adversarial debiasing aims to mitigate biases in machine learning models, ensuring fairer and more equitable outcomes across different demographic groups. Current research focuses on developing and refining adversarial training techniques, often incorporating generative adversarial networks (GANs) or employing specialized architectures like fair message passing (FMP) within graph neural networks (GNNs) to address biases in various data types, including images, text, and graph data. This work is crucial for improving the trustworthiness and reliability of AI systems across diverse applications, particularly in sensitive domains like healthcare and finance, where biased predictions can have significant real-world consequences. The ultimate goal is to achieve a balance between model accuracy and fairness, minimizing the impact of spurious correlations and promoting equitable outcomes.

Papers

October 3, 2024

Achieving Fairness in Predictive Process Analytics via Adversarial Learning
Massimiliano de Leoni, Alessandro Padella
Procedural Fairness Adversarial Learning Process Mining Biased Prediction Adversarial Debiasing Predictive Process

August 28, 2024

CSAD: Unsupervised Component Segmentation for Logical Anomaly Detection
Yu-Hsuan Hsieh, Shang-Hong Lai
Anomaly Detection Segmentation Method Adversarial Debiasing Lightweight Semantic Segmentation Sub Component Level Segmentation

August 12, 2024

Towards Adversarial Robustness via Debiased High-Confidence Logit Alignment
Kejia Zhang, Juanjuan Weng, Zhiming Luo, Shaozi Li
Adversarial Attack Adversarial Example Adversarial Robustness Adversarial Debiasing

April 11, 2024

3D-CSAD: Untrained 3D Anomaly Detection for Complex Manufacturing Surfaces
Xuanming Cao, Chengyu Tao, Juan Du
Point Cloud Unsupervised Anomaly Detection Object Surface Point Cloud Data 3D Anomaly Adversarial Debiasing Surface Inspection

January 23, 2024

MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakage
Ying Song, Balaji Palanisamy
Graph Neural Network Area MaPPing Adversarial Debiasing

January 15, 2024

Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video
Zhaobo Qi, Yibo Yuan, Xiaowen Ruan, Shuhui Wang, Weigang Zhang, Qingming Huang
Source Video Temporal Sentence Grounding Adversarial Debiasing Bias Aligned Sample Visual Bias

December 26, 2023

Practical Bias Mitigation through Proxy Sensitive Attribute Label Generation
Bhushan Chaudhary, Anubha Pandey, Deepak Bhatt, Darshika Tiwari
Bias Mitigation Adversarial Debiasing Bias Mitigation Algorithm Proxy Label

December 19, 2023

Chasing Fairness in Graphs: A GNN Architecture Perspective
Zhimeng Jiang, Xiaotian Han, Chao Fan, Zirui Liu, Na Zou, Ali Mostafavi, Xia Hu
Graph Drawing Node Classification GNN Architecture Fair Representation Adversarial Debiasing Fair Contrastive

October 27, 2023

On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
Vincent Grari, Thibault Laugel, Tatsunori Hashimoto, Sylvain Lamprier, Marcin Detyniecki
Robust Optimization Algorithmic Fairness Fairness Notion Adversarial Debiasing Fair Adversarial Fairness Learning Local Fairness

July 4, 2023

Prompt Tuning Pushes Farther, Contrastive Learning Pulls Closer: A Two-Stage Approach to Mitigate Social Biases
Yingji Li, Mengnan Du, Xin Wang, Ying Wang
Contrastive Learning Pre Trained Language Model Prompt Tuning Social Bias Debiasing Method Data Debiasing Two Stage Approach Adversarial Debiasing

April 25, 2023

Out-of-distribution Evidence-aware Fake News Detection via Dual Adversarial Debiasing
Qiang Liu, Junfei Wu, Shu Wu, Liang Wang
Fake News Detection Systematic Bias Adversarial Debiasing Evidence Detection Evidence Aware Fake News Detection

November 18, 2022

On the Alignment of Group Fairness with Attribute Privacy
Jan Aalmoes, Vasisht Duddu, Antoine Boutet
Alignment Problem Group Fairness Inference Attack Adversarial Debiasing Attribute Privacy

September 20, 2022

Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendation
Clara Rus, Jeffrey Luppes, Harrie Oosterhuis, Gido H. Schoenmacker
Algorithmic Bias Fair Representation Job Recommendation Adversarial Debiasing Fair Adversarial Fairness Aware Recommendation

March 22, 2022

A Prompt Array Keeps the Bias Away: Debiasing Vision-Language Models with Adversarial Learning
Hugo Berg, Siobhan Mackenzie Hall, Yash Bhalgat, Wonsuk Yang, Hannah Rose Kirk, Aleksandar Shtedritski, Max Bain
Vision Language Model Absolute Stance Bias Contrastive Loss Adversarial Learning Bias Measurement Adversarial Debiasing Image Text Representation Prompt Programming

March 12, 2022

Towards Equal Opportunity Fairness through Adversarial Learning
Xudong Han, Timothy Baldwin, Trevor Cohn
Adversarial Training Adversarial Learning Bias Mitigation Adversarial Debiasing Standard Adversarial Training

February 8, 2022

FMP: Toward Fair Graph Message Passing against Topology Bias
Zhimeng Jiang, Xiaotian Han, Chao Fan, Zirui Liu, Na Zou, Ali Mostafavi, Xia Hu
Fair Representation Fairness Objective Graph Topology Adversarial Debiasing

November 16, 2021

Two-step adversarial debiasing with partial learning -- medical image case-studies
Ramon Correa, Jiwoong Jason Jeong, Bhavik Patel, Hari Trivedi, Judy W. Gichoya, Imon Banerjee
Medical Imaging Implicit Bias AI Model Adversarial Debiasing Bias Reduction Two Step