Reproducibility study of FairAC

TL;DR

This paper conducts a reproducibility study of FairAC, confirming its generalizability and fairness improvements across datasets, while refactoring its codebase for broader applicability.

Contribution

It provides a reproducibility assessment of FairAC, demonstrating its robustness and extending its usability through code refactoring.

Findings

FairAC's results are reproducible across datasets.

FairAC improves group fairness without harming individual fairness.

Refactored code enhances applicability to various models.

Abstract

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.