.png){kind=icon}
返回
Learning Fair Representations via Distance Correlation Minimization
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2022.3187165.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
As machine learning algorithms are increasingly deployed for high-impact automated decision-making, the presence of bias (in datasets or tasks) gradually becomes one of the most critical challenges in machine learning applications. Such challenges range from the bias of race in face recognition to the bias of gender in hiring systems, where race and gender can be denoted as sensitive attributes. In recent years, much progress has been made in ensuring fairness and reducing bias in standard machine learning settings. Among them, learning fair representations with respect to the sensitive attributes has attracted increasing attention due to its flexibility in learning the rich representations based on advances in deep learning. In this article, we propose graph-fair, an algorithmic approach to learning fair representations under the graph Laplacian regularization, which reduces the separation between groups and the clustering within a group by encoding the sensitive attribute information into the graph. We have theoretically proved the underlying connection between graph regularization and distance correlation and show that the latter can be regarded as a standardized version of the former, with an additional advantage of being scale-invariant. Therefore, we naturally adopt the distance correlation as the fairness constraint to decrease the dependence between sensitive attributes and latent representations, called dist-fair. In contrast to existing approaches using measures of dependency and adversarial generators, both graph-fair and dist-fair provide simple fairness constraints, which eliminate the need for parameter tuning (e.g., choosing kernels) and introducing adversarial networks. Experiments conducted on real-world corpora indicate that our proposed fairness constraints applied for representation learning can provide better tradeoffs between fairness and utility results than existing approaches.
Keyword:
Representation learning
Correlation
Feature extraction
Task analysis
Laplace equations
Learning systems
Encoding
Distance correlation
fair representation learning
graph Laplacian regularization
sensitive attributes
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
GIT1 promotes lung cancer cell metastasis through modulating Rac1/Cdc42 activity and is associated with poor prognosis.png)
Oncotarget
OAAI
OncotargetIF0
OAAI分享收藏Semi-Supervised Graph Regularized Deep NMF With Bi-Orthogonal Constraints for Data Representation
PREAI
分享收藏
查看更多内容