arpitdm/gnn_accuracy_fairness_tradeoff: v0.1.0-alpha

dc.contributor.affiliationICREA, Universitat Pompeu Fabra-Carlos Castillo
dc.contributor.authorCarlos Castillo
dc.date.accessioned2025-04-29T14:02:42Z
dc.date.issued2023-08-16
dc.date.issued2023-08-16
dc.descriptionReference code and data for analyzing the tradeoff between accuracy and algorithmic fairness on graph neural networks for node classification. This repository provides support for downloading and preprocessing four datasets (German, Credit, Penn94, and Pokec-Z), building and training three GNN models (GCN, GraphSAGE, and GIN), and implementing algorithmic fairness interventions including PFR-AX and PostProcess (ours), Unaware, EDITS, and NIFTY (baselines).  
dc.identifierhttps://doi.org/10.5281/zenodo.8252028
dc.identifier.urihttps://datakatalogi.helsinki.fi/handle/123456789/5314
dc.rights.licenseother-open
dc.subjectGraph Neural Networks
dc.subjectNode Classification
dc.subjectAlgorithmic Fairness
dc.titlearpitdm/gnn_accuracy_fairness_tradeoff: v0.1.0-alpha
dc.typesoftware
Zenodo


: