Modeling Techniques for Machine Learning Fairness: A Survey
arXiv:2111.03015
Abstract
Machine learning models are becoming pervasive in high-stakes applications. Despite their clear benefits in terms of performance, the models could show discrimination against minority groups and result in fairness issues in a decision-making process, leading to severe negative impacts on the individuals and the society. In recent years, various techniques have been developed to mitigate the unfairness for machine learning models. Among them, in-processing methods have drawn increasing attention from the community, where fairness is directly taken into consideration during model design to induce intrinsically fair models and fundamentally mitigate fairness issues in outputs and representations. In this survey, we review the current progress of in-processing fairness mitigation techniques. Based on where the fairness is achieved in the model, we categorize them into explicit and implicit methods, where the former directly incorporates fairness metrics in training objectives, and the latter focuses on refining latent representation learning. Finally, we conclude the survey with a discussion of the research challenges in this community to motivate future exploration.
arXiv comment26 pages, 4 figures
References in corpus (20)
- Counterfactual Fairness
- Fairness in Machine Learning: A Survey
- Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
- Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization
- On Fairness and Calibration
- Fairness Without Demographics in Repeated Loss Minimization
- A Convex Framework for Fair Regression
- Achieving Fairness through Adversarial Learning: an Application to Recidivism Prediction
- Censoring Representations with an Adversary
- Compositional Fairness Constraints for Graph Embeddings
- Fairness Through Computationally-Bounded Awareness
- FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders
- Bias In, Bias Out? Evaluating the Folk Wisdom
- Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems
- Wasserstein Fair Classification
- Directional Bias Amplification
- Adversarial Removal of Demographic Attributes from Text Data
- Fairness-Aware Node Representation Learning
- Counterfactual fairness: removing direct effects through regularization
- Fairness in TabNet Model by Disentangled Representation for the Prediction of Hospital No-Show