PolyNSD defines sheaf diffusion as a trainable convex combination of K+1 orthogonal polynomial responses on a spectrally rescaled normalized sheaf Laplacian, enabling stable K-hop propagation with diagonal restriction maps.
What we want in PolyNSD is anoperatorapproximation of a spectral multiplier f(L), with σ(L)⊂[0, λ max]
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves
PolyNSD defines sheaf diffusion as a trainable convex combination of K+1 orthogonal polynomial responses on a spectrally rescaled normalized sheaf Laplacian, enabling stable K-hop propagation with diagonal restriction maps.