Fairness Optimization

Fairness optimization in machine learning aims to mitigate algorithmic bias, ensuring models make equitable predictions across different demographic groups. Current research focuses on integrating fairness constraints into model training, employing techniques like bi-level optimization, data augmentation, and graph modification to achieve this goal across various model architectures, including deep neural networks and recommendation systems. These efforts are crucial for addressing societal biases embedded in data and promoting the development of responsible and ethical AI systems, impacting fields ranging from healthcare to finance.

Papers

December 15, 2023

Coupling Fairness and Pruning in a Single Run: a Bi-level Optimization Perspective
Yucong Dai, Gen Li, Feng Luo, Xiaolong Ma, Yongkai Wu
Edge Pruning Fairness Constraint Structured Pruning Model Fairness Bi Level Optimization Sparse Deep Fairness Optimization

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

February 13, 2023

Improving Recommendation Fairness via Data Augmentation
Lei Chen, Le Wu, Kun Zhang, Richang Hong, Defu Lian, Zhiqiang Zhang, Jun Zhou, Meng Wang
Data Augmentation Collaborative Filtering Recommendation Model Data Balancing Recommendation Fairness Fairness Aware Recommendation Fairness Optimization

April 28, 2022

Probabilistic Permutation Graph Search: Black-Box Optimization for Fairness in Ranking
Ali Vardasbi, Fatemeh Sarvi, Maarten de Rijke
Procedural Fairness Black Box Optimization Partial Ranking Fairness Metric Probabilistic Ranking Ranking Performance Fairness Optimization

January 27, 2022

FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modification
Sean Current, Yuntian He, Saket Gurukar, Srinivasan Parthasarathy
Graph Neural Network Link Prediction Effective Recommendation Inherent Bias Recommendation Fairness Graph Injection Attack Fairness Optimization

Fairness Optimization

Papers

Coupling Fairness and Pruning in a Single Run: a Bi-level Optimization Perspective

Fair Few-shot Learning with Auxiliary Sets

Improving Recommendation Fairness via Data Augmentation

Probabilistic Permutation Graph Search: Black-Box Optimization for Fairness in Ranking

FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modification