omnibias.graph.torch.ops
Spectral graph operators and differentiable relaxations for ordering, assignment, and graph-structured learning.
import omnibias.graph.torch.opsModule contract & mathematical conventions
Torch differentiable-graph operator surface.
Shared formulas do not imply universal floating-point identity. Verify dtype, shape, derivative-order support, and the stated numerical assumptions for the path you use.
Imports & aliases
These names share a definition with another public module. Follow a name for its full contract, parameters, and examples.
| Import from this module | Canonical reference |
|---|---|
CutRelaxation | omnibias.graph.torch.ops.CutRelaxation |
degree | omnibias.graph.torch.ops.degree |
fiedler_vector | omnibias.graph.torch.ops.fiedler_vector |
graph_heat_kernel | omnibias.graph.torch.ops.graph_heat_kernel |
graph_laplacian | omnibias.graph.torch.ops.graph_laplacian |
gumbel_sinkhorn | omnibias.graph.torch.ops.gumbel_sinkhorn |
laplacian_spectrum | omnibias.graph.torch.ops.laplacian_spectrum |
normalized_laplacian | omnibias.graph.torch.ops.normalized_laplacian |
random_walk_laplacian | omnibias.graph.torch.ops.random_walk_laplacian |
sample_gumbel | omnibias.graph.torch.ops.sample_gumbel |
sinkhorn_normalize | omnibias.graph.torch.ops.sinkhorn_normalize |
soft_sort | omnibias.graph.torch.ops.soft_sort |
soft_sort_permutation | omnibias.graph.torch.ops.soft_sort_permutation |
soft_top_k | omnibias.graph.torch.ops.soft_top_k |
spectral_clustering_relaxation | omnibias.graph.torch.ops.spectral_clustering_relaxation |
spectral_embedding | omnibias.graph.torch.ops.spectral_embedding |