A modified graph Laplacian incorporating subspace projections, spectral adjustments, and frequency-based filtering is proposed to improve fairness in diffusion-based graph neural networks while preserving competitive performance.
arXiv preprint arXiv:2207.04376 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Geometrical fairness in graph neural networks
A modified graph Laplacian incorporating subspace projections, spectral adjustments, and frequency-based filtering is proposed to improve fairness in diffusion-based graph neural networks while preserving competitive performance.