.png){kind=icon}
返回
FAIR: Fair adversarial instance re-weighting
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2021.12.082.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
With growing awareness of societal impact of artificial intelligence, fairness has become an important aspect of machine learning algorithms. The issue is that human biases towards certain groups of popu-lation, defined by sensitive features like race and gender, are introduced to the training data through data collection and labeling. Two important directions of fairness ensuring research have focused on (i) instance weighting in order to decrease the impact of more biased instances and (ii) adversarial training in order to construct data representations informative of the target variable, but uninformative of the sensitive attributes. In this paper we propose a Fair Adversarial Instance Re-weighting (FAIR) method, which uses adversarial training to learn instance weighting function that ensures fair predictions. Merging the two paradigms, it inherits desirable properties from both interpretability of reweighting and end-to-end trainability of adversarial training. We propose four different variants of the method and, among other things, demonstrate how the method can be cast in a fully probabilistic framework. Additionally, theoretical analysis of FAIR models' properties is provided. We compare FAIR models to ten other related and state-of-the-art models and demonstrate that FAIR is able to achieve a better trade-off between accuracy and unfairness. To the best of our knowledge, this is the first model that merges reweighting and adversarial approaches by means of a weighting function that can provide inter-pretable information about fairness of individual instances. (c) 2021 Published by Elsevier B.V.
Keyword:
Fairness
Adversarial training
Instance reweighting
Deep learning
Classification
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6.5
论文数:
2.5W
被引数:
6.5W
机构
引用论文
TabFairGAN: Fair Tabular Data Generation with Generative Adversarial NetworksTabFairGAN: 使用生成对抗网络生成公平的表格数据
OAAI
.png){kind=icon}
OAAI分享收藏Cumulative learning and sustained engagement in an introduction to accounting course会计入门课程中的累积学习与持续参与
PREAI
分享收藏Principal features of the mating system of a large spawning aggregation of the giant Australian cuttlefish Sepia apama (Mollusca: Cephalopoda)大型澳大利亚墨鱼乌贼棕褐色 (软体动物: 头足类) 的大型产卵聚集的交配系统的主要特征
PREAI
分享收藏
查看更多内容