Summary of Reproducibility Study Of Fairac, by Gijs De Jong et al.
Reproducibility study of FairAC
by Gijs de Jong, Macha J. Meijer, Derck W. E. Prinzhorn, Harold Ruiter
First submitted to arxiv on: 5 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper aims to reproduce and extend the findings of “Fair Attribute Completion on Graph with Missing Attributes” by Guo et al. The authors investigate the claims made in the original paper, finding that they hold true. They also demonstrate FairAC’s generalizability to various datasets and sensitive attributes, showing improvements in group fairness without sacrificing individual fairness. Moreover, the refactored codebase of FairAC enables its easy applicability for different datasets and models. The study highlights FairAC’s potential as a generic framework for various downstream tasks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at a research project called Fair Attribute Completion on Graph with Missing Attributes. It wants to see if the results from that project are real or just lucky. They found that the original findings are true, and also showed that this method can be used in many different situations without affecting individual fairness. The code for this method has been improved so it’s easier to use with different data sets and models. |
