Factoring the matrix of domination: A critical review and reimagination of intersectionality in ai fairness
Intersectionality is a critical framework that, through inquiry and praxis, allows us to examine
how social inequalities persist through domains of structure and discipline. Given AI fairness' …
how social inequalities persist through domains of structure and discipline. Given AI fairness' …
Learning fair representations via rebalancing graph structure
Abstract Graph Neural Network (GNN) models have been extensively researched and
utilised for extracting valuable insights from graph data. The performance of fairness …
utilised for extracting valuable insights from graph data. The performance of fairness …
A survey on intersectional fairness in machine learning: Notions, mitigation, and challenges
The widespread adoption of Machine Learning systems, especially in more decision-critical
applications such as criminal sentencing and bank loans, has led to increased concerns …
applications such as criminal sentencing and bank loans, has led to increased concerns …
Improving fairness in ai models on electronic health records: The case for federated learning methods
Developing AI tools that preserve fairness is of critical importance, specifically in high-stakes
applications such as those in healthcare. However, health AI models' overall prediction …
applications such as those in healthcare. However, health AI models' overall prediction …
Fairness-aware clique-preserving spectral clustering of temporal graphs
With the widespread development of algorithmic fairness, there has been a surge of
research interest that aims to generalize the fairness notions from the attributed data to the …
research interest that aims to generalize the fairness notions from the attributed data to the …
Intersectional Two-sided Fairness in Recommendation
Fairness of recommender systems (RS) has attracted increasing attention recently. Based
on the involved stakeholders, the fairness of RS can be divided into user fairness, item …
on the involved stakeholders, the fairness of RS can be divided into user fairness, item …
Mining bias-target Alignment from Voronoi Cells
R Nahon, VT Nguyen… - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Despite significant research efforts, deep neural networks remain vulnerable to biases: this
raises concerns about their fairness and limits their generalization. In this paper, we propose …
raises concerns about their fairness and limits their generalization. In this paper, we propose …
MultiFair: Model Fairness With Multiple Sensitive Attributes
While existing fairness interventions show promise in mitigating biased predictions, most
studies concentrate on single-attribute protections. Although a few methods consider …
studies concentrate on single-attribute protections. Although a few methods consider …
Integrating Fair Representation Learning with Fairness Regularization for Intersectional Group Fairness
In the pursuit of intersectional group fairness in machine learning models, significant
attention has been directed towards fair representation learning methods. These methods …
attention has been directed towards fair representation learning methods. These methods …
Dealing with Data Bias in Classification: Can Generated Data Ensure Representation and Fairness?
Fairness is a critical consideration in data analytics and knowledge discovery because
biased data can perpetuate inequalities through further pipelines. In this paper, we propose …
biased data can perpetuate inequalities through further pipelines. In this paper, we propose …