复现研究验证了图公平表示学习框架的可靠性与扩展性。
Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations
- 通过自动化数据增强提升图神经网络的公平性表现
- 在子群体层面实现更优的公平-准确权衡
- 验证并拓展了原方法在链接预测任务中的适用性
本研究对Ling等（2022）提出的《基于自动化数据增强的图表示公平学习》进行可复现性分析，重点评估其在节点分类任务上的原始结论，并探索Graphair框架在链接预测任务中的表现。结果显示，三个核心主张中一个可部分复现，其余两个可完全验证。同时，我们将Graphair的应用从节点分类拓展至多种数据集上的链接预测任务。结果表明，尽管在混合二元公平性下，Graphair与基线模型具有相近的公平-准确权衡；但在子群体二元公平性下，其表现显著更优。这些发现证实了Graphair在图学习中的广泛潜力。代码已开源至GitHub：https://github.com/juellsprott/graphair-reproducibility。
原文摘要 · Abstract (English)
In this study, we undertake a reproducibility analysis of 'Learning Fair Graph Representations Via Automated Data Augmentations' by Ling et al. (2022). We assess the validity of the original claims focused on node classification tasks and explore the performance of the Graphair framework in link prediction tasks. Our investigation reveals that we can partially reproduce one of the original three claims and fully substantiate the other two. Additionally, we broaden the application of Graphair from node classification to link prediction across various datasets. Our findings indicate that, while Graphair demonstrates a comparable fairness-accuracy trade-off to baseline models for mixed dyadic-level fairness, it has a superior trade-off for subgroup dyadic-level fairness. These findings underscore Graphair's potential for wider adoption in graph-based learning. Our code base can be found on GitHub at https://github.com/juellsprott/graphair-reproducibility.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。