Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Nijdam, Thijmen, Sprott, Juell, Papandreou-Lazos, Taiki, de Heus, Jurgen
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916381552803840
author Nijdam, Thijmen
Sprott, Juell
Papandreou-Lazos, Taiki
de Heus, Jurgen
author_facet Nijdam, Thijmen
Sprott, Juell
Papandreou-Lazos, Taiki
de Heus, Jurgen
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_00421
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations
Nijdam, Thijmen
Sprott, Juell
Papandreou-Lazos, Taiki
de Heus, Jurgen
Machine Learning
Computers and Society
Social and Information Networks
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.
title Reproducibility Study Of Learning Fair Graph Representations Via Automated Data Augmentations
topic Machine Learning
Computers and Society
Social and Information Networks
url https://arxiv.org/abs/2409.00421