.png){kind=icon}
返回
FairDRO: Group fairness regularization via classwise robust optimization
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2024.106891.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Existing group fairness-aware training methods fall into two categories: re-weighting underrepresented groups according to certain rules, or using regularization terms such as smoothed approximations of fairness metrics or surrogate statistical quantities. While each category has its own strength inapplicability or performance when compared to each other, their successful performances are typically limited to specific cases. To that end, we propose a new approach called FairDRO, which takes advantage of both categories through a classwise group distributionally robust optimization (DRO) framework. Our method unifies re-weighting and regularization by incorporating a well-justified group fairness metric into the objective as regularization, but solving it through a principled re-weighting strategy. To optimize our resulting objective efficiently, we adopt an iterative algorithm and consequently develop two variants of FairDRO algorithm depending on the choice of surrogate loss. For in-depth understanding, we derive three theoretical results: (i) a closed-form solution for the correct re-weights; (ii) justifications for using the surrogate losses; and (iii) a convergence analysis of our method. Experimental results show that our algorithms consistently achieve state-of-the-art performance inaccuracy- fairness trade-offs across multiple benchmarks, demonstrating scalability and broad applicability compared to existing methods.
Keyword:
Trustworthy
Artificial intelligence
Group fairness
In-processing
Distributionally robust optimization
期刊
IF:
6.3
论文数:
8.2K
被引数:
3.0W
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分享收藏分享收藏分享收藏Tachykinin and Calcitonin Gene-Related Peptide Immunoreactivities and Mrnas in the Mammalian Enteric Nervous System and Sensory Ganglia哺乳动物肠神经系统和感觉神经节中的速激肽和降钙素基因相关肽的免疫反应性和mrna
PREAI
分享收藏NMR spectra of aromatic amines and amides-I Correlations of amino proton shifts with Hammett substituents constants with Hückel electron densitiesTetrahedron
TetrahedronIF0
PREAI
分享收藏Disentangling in vivo the effects of iron content and atrophy on the ageing human brainNeuroImage
OAAI
NeuroImageIF0
OAAI分享收藏
查看更多内容