Crate propago 

propago: graph learning primitives on Burn tensors.

Provides Poincare ball geometry and graph convolution layers that run on any Burn backend (ndarray, wgpu, tch, etc.).

• PoincareBall: hyperbolic geometry ops (project, mobius_add, exp/log maps, hyperbolic activation via PoincareBall::hyp_act)
• GCNConv: graph convolutional layer (linear + adjacency matmul)
• HGCNConv: hyperbolic graph convolution on the Poincare ball, with optional activation via HGCNConv::forward_act

Re-exports

pub use hyperbolic::PoincareBall;

pub use nn::GCNConv;

pub use nn::HGCNConv;

Modules

hyperbolic

Poincare ball geometry on Burn tensors.

nn

Graph neural network layers on Burn tensors.