FAROS switches sensitive attributes on an optimal fraction of nodes at an optimal diffusion step to produce fairer generated graphs with little accuracy loss.
Graph neural networks are inherently good generalizers: Insights by bridging GNNs and MLPs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FAROS: Fair Graph Generation via Attribute Switching Mechanisms
FAROS switches sensitive attributes on an optimal fraction of nodes at an optimal diffusion step to produce fairer generated graphs with little accuracy loss.