Exploring the Unfairness of DP-SGD Across Settings
원문 초록
End users and regulators require private and fair artificial intelligence models, but previous work suggests these objectives may be at odds. We use the CivilComments to evaluate the impact of applying the {\em de facto} standard approach to privacy, DP-SGD, across several fairness metrics. We evaluate three implementations of DP-SGD: for dimensionality reduction (PCA), linear classification (logistic regression), and robust deep learning (Group-DRO). We establish a negative, logarithmic correlation between privacy and fairness in the case of linear classification and robust deep learning. DP-SGD had no significant impact on fairness for PCA, but upon inspection, also did not seem to lead to private representations.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Active Learning for Manifold Gaussian Process Regression
Meta Optimality for Demographic Parity Constrained Regression via Post-Processing
An Interpretable Adaptive Multiscale Attention Deep Neural Network for Tabular Data
SONNET: A Self-Guided Ordinal Regression Neural Network for Segmentation and Classification of Nuclei in Large-Scale Multi-Tissue Histology Images
Fuzzy Pooling
A Reproducibility Study of Product-side Fairness in Bundle Recommendation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.