标题： 通过自动化数据增强学习公平图表示的可重复性研究 显示英文标题

标题： Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations

摘要： 本研究对 Ling 等人（2022）的《通过自动化数据增强学习公平图表示》一文进行了可重复性分析。我们评估了该研究中针对节点分类任务提出的原始主张的有效性，并探索了 Graphair 框架在链路预测任务中的性能。我们的研究表明，可以部分重现其中一个原始的三个主张，而另外两个主张则得到了完全验证。此外，我们将 Graphair 的应用范围从节点分类扩展到了各种数据集上的链路预测。我们的发现表明，尽管 Graphair 在混合二元级别公平性方面与基线模型展示了相当的公平性-准确性权衡，但在子组二元级别公平性方面具有更优的权衡。这些发现突显了 Graphair 在基于图的学习中更广泛应用的潜力。我们的代码库可以在 GitHub 上找到：https://github.com/juellsprott/graphair-reproducibility。 显示英文摘要

摘要： 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.