Individual Fairness with Group Awareness Under Uncertainty
被引:0
|
作者:
Wang, Zichong
论文数: 0引用数: 0
h-index: 0
机构:
Florida Int Univ, Miami, FL 33199 USAFlorida Int Univ, Miami, FL 33199 USA
Wang, Zichong
[1
]
Dzuong, Jocelyn
论文数: 0引用数: 0
h-index: 0
机构:
Florida Int Univ, Miami, FL 33199 USAFlorida Int Univ, Miami, FL 33199 USA
Dzuong, Jocelyn
[1
]
Yuan, Xiaoyong
论文数: 0引用数: 0
h-index: 0
机构:
Clemson Univ, Clemson, SC USAFlorida Int Univ, Miami, FL 33199 USA
Yuan, Xiaoyong
[2
]
Chen, Zhong
论文数: 0引用数: 0
h-index: 0
机构:
Southern Illinois Univ, Carbondale, IL USAFlorida Int Univ, Miami, FL 33199 USA
Chen, Zhong
[3
]
Wu, Yanzhao
论文数: 0引用数: 0
h-index: 0
机构:
Florida Int Univ, Miami, FL 33199 USAFlorida Int Univ, Miami, FL 33199 USA
Wu, Yanzhao
[1
]
Yao, Xin
论文数: 0引用数: 0
h-index: 0
机构:
Lingnan Univ, Hong Kong, Peoples R ChinaFlorida Int Univ, Miami, FL 33199 USA
Yao, Xin
[4
]
Zhang, Wenbin
论文数: 0引用数: 0
h-index: 0
机构:
Florida Int Univ, Miami, FL 33199 USAFlorida Int Univ, Miami, FL 33199 USA
Zhang, Wenbin
[1
]
机构:
[1] Florida Int Univ, Miami, FL 33199 USA
[2] Clemson Univ, Clemson, SC USA
[3] Southern Illinois Univ, Carbondale, IL USA
[4] Lingnan Univ, Hong Kong, Peoples R China
来源:
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES: RESEARCH TRACK, PT V, ECML PKDD 2024
|
2024年
/
14945卷
基金:
美国国家科学基金会;
关键词:
Censorship;
Group fairness;
Individual fairness;
SURVIVAL;
D O I:
10.1007/978-3-031-70362-1_6
中图分类号:
TP18 [人工智能理论];
学科分类号:
081104 ;
0812 ;
0835 ;
1405 ;
摘要:
As machine learning (ML) extends its influence across diverse societal realms, the need to ensure fairness within these systems has markedly increased, reflecting notable advancements in fairness research. However, most existing fairness studies exclusively optimize either individual fairness or group fairness, neglecting the potential impact on one aspect while enforcing the other. In addition, most of them operate under the assumption of having full access to class labels, a condition that often proves impractical in real-world applications due to censorship. This paper delves into the concept of individual fairness amidst censorship and also with group awareness. We argue that this setup provides a more realistic understanding of fairness that aligns with real-world scenarios. Through experiments conducted on four real-world datasets with socially sensitive concerns and censorship, we demonstrate that our proposed approach not only outperforms state-of-the-art methods in terms of fairness but also maintains a competitive level of predictive performance.