arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.03314cs.LGcs.AI
收藏

FairAC 的可复现性研究

Reproducibility study of FairAC

University of Amsterdam(阿姆斯特丹大学)

Gijs de Jong, Macha J. Meijer, Derck W. E. Prinzhorn, Harold Ruiter

AI总结:

本文复现了 FairAC 框架,验证其原论文结果可复现,并证明该框架可泛化到多种数据集与敏感属性,且群体公平性的提升不以牺牲个体公平性为代价。

摘要:

本研究旨在通过检验 Guo、Chu 和 Li 所著论文《Fair Attribute Completion on Graph with Missing Attributes》(arXiv:2302.12977)中提出的主张,复现该论文的研究结果。本文表明,原论文的结果是可复现的,因此其主张成立。然而,关于 FairAC 是适用于许多下游任务的通用框架这一说法非常宽泛,因此只能进行部分验证。此外,我们证明 FairAC 能够泛化到各种数据集和敏感属性,并提供证据表明 FairAC 框架在群体公平性方面的提升并非以牺牲个体公平性为代价。最后,FairAC 的代码库已经过重构,现在可以方便地应用于各种数据集和模型。

英文摘要:

This work aims to reproduce the findings of the paper "Fair Attribute Completion on Graph with Missing Attributes" written by Guo, Chu, and Li arXiv:2302.12977 by investigating the claims made in the paper. This paper suggests that the results of the original paper are reproducible and thus, the claims hold. However, the claim that FairAC is a generic framework for many downstream tasks is very broad and could therefore only be partially tested. Moreover, we show that FairAC is generalizable to various datasets and sensitive attributes and show evidence that the improvement in group fairness of the FairAC framework does not come at the expense of individual fairness. Lastly, the codebase of FairAC has been refactored and is now easily applicable for various datasets and models.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑