Fair and Privacy-Preserving Graph Neural Network

Wang, Xuemin; Gu, Tianlong; Bao, Xuguang; Chen, Liang

doi:10.1007/978-3-031-30678-5_64

Cited by 3 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First our fairness metric is based on the concept of excessive risk which is widely used as the benchmark metric to measure the utility of private learning Pathak et al [2010]; Wang et al [2018]; Cattan et al [2022]. The excessive risk is also referred as utility in other work Chourasia et al [2021]; Wang et al [2019]. The excessive risk measures the difference in accuracy between private and non-private models over the population.…”

Section: On the Fairness Impacts Of Private Ensembles Models Suppleme...mentioning

confidence: 99%

Decision Making with Differential Privacy under a Fairness Lens

Tran

Fioretto

Hentenryck

et al. 2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

Many agencies release datasets and statistics about groups of individuals that are used as input to a number of critical decision processes. To conform with privacy and confidentiality requirements, these agencies are often required to release privacy-preserving versions of the data. This paper studies the release of differentially private datasets and analyzes their impact on some critical resource allocation tasks under a fairness perspective. The paper shows that, when the decisions take as input differentially private data, the noise added to achieve privacy disproportionately impacts some groups over others. The paper analyzes the reasons for these disproportionate impacts and proposes guidelines to mitigate these effects. The proposed approaches are evaluated on critical decision problems that use differentially private census data.

show abstract

Section: On the Fairness Impacts Of Private Ensembles Models Suppleme...mentioning

confidence: 99%

Decision Making with Differential Privacy under a Fairness Lens

Tran

Fioretto

Hentenryck

et al. 2021

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

show abstract

A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications

Zhang,

Zhao,

et al. 2024

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Fairness-Aware Graph Neural Networks: A Survey

Chen,

Rossi,

Park

et al. 2024

ACM Trans. Knowl. Discov. Data

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have become increasingly important due to their representational power and state-of-the-art predictive performance on many fundamental learning tasks. Despite this success, GNNs suffer from fairness issues that arise as a result of the underlying graph data and the fundamental aggregation mechanism that lies at the heart of the large class of GNN models. In this article, we examine and categorize fairness techniques for improving the fairness of GNNs. We categorize these techniques by whether they focus on improving fairness in the pre-processing, in-processing (during training), or post-processing phases. Furthermore, we discuss how such techniques can be used together whenever appropriate, and highlight the advantages and intuition as well. We also introduce an intuitive taxonomy for fairness evaluation metrics including graph-level fairness, neighborhood-level fairness, embedding-level fairness, and prediction-level fairness metrics. In addition, graph datasets that are useful for benchmarking the fairness of GNN models are summarized succinctly. Finally, we highlight key open problems and challenges that remain to be addressed.

show abstract

Fair and Privacy-Preserving Graph Neural Network

Cited by 3 publications

References 4 publications

Decision Making with Differential Privacy under a Fairness Lens

Decision Making with Differential Privacy under a Fairness Lens

A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications

Fairness-Aware Graph Neural Networks: A Survey

Contact Info

Product

Resources

About