Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations

TL;DR

This paper conducts a reproducibility analysis of the Graphair framework, validating its claims on node classification and extending its application to link prediction, revealing its strengths in subgroup fairness and potential for broader use.

Contribution

It provides a reproducibility assessment of Graphair, extends its application to link prediction, and compares its fairness-accuracy trade-offs across datasets.

Findings

Partial reproduction of original claims

Full validation of remaining claims

Graphair shows superior subgroup fairness trade-off

Abstract

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.