based off of ogb NodePropPredDataset https://github.com/snap-stanford/ogb/blob/master/ogb/nodeproppred/dataset.py Gives torch

Initializes a TransConvLayer instance. Args: manifold: The manifold to use for the layer. in_channels: The n

Initialize a Lorentz manifold with k, curvature is -1/k. Parameters: k (float): Curvature parameter of the manifold.

Initializes a HypFormer object. Args: in_channels (int): The number of input channels. hidden_channels (int)

Initialize a Lorentz manifold with curvature k. Parameters: k (float): Curvature of the manifold. learnable

Check if a point lies on the manifold. Parameters: x (torch.Tensor): Point to check. atol (float): Absolute

Check if a point lies on the manifold. Parameters: x (torch.Tensor): Point to check. atol (float): Absolute

Check if a vector lies on the tangent space at a point. Parameters: x (torch.Tensor): Point on the manifold.

Check if a vector lies on the tangent space at a point. Parameters: x (torch.Tensor): Point on the manifold.

Numerically stable arccosh that never returns NaNs. :param x: The input tensor. :return: log(x + sqrt(max(x^2 - 1, eps))

Numerically stable arccosh that never returns NaNs. :param x: The input tensor. :return: log(x + sqrt(max(x^2 - 1, eps))

Numerically stable arccosh that never returns NaNs. :param x: The input tensor. :return: log(x + sqrt(max(x^2 - 1, eps))

Numerically stable arctanh that never returns NaNs. :param x: The input tensor. :return: log(x + sqrt(max(x^2 - 1, eps))

Numerically stable arctanh that never returns NaNs. :param x: The input tensor. :return: log(x + sqrt(max(x^2 - 1, eps))

Numerically stable arctanh that never returns NaNs. :param x: The input tensor. :return: log(x + sqrt(max(x^2 - 1, eps))

Apply numpy broadcasting rules to shapes.

Apply numpy broadcasting rules to shapes.

Apply numpy broadcasting rules to shapes.

Get a canonical manifold. If a manifold is wrapped with Scaled. Some attributes may not be available. This should help if you really need th

Get a canonical manifold. If a manifold is wrapped with Scaled. Some attributes may not be available. This should help if you really need th

Get a canonical manifold. If a manifold is wrapped with Scaled. Some attributes may not be available. This should help if you really need th

Computes the pairwise geodesic distance between two sets of points x and y.

Computes the pairwise geodesic distance between two sets of points x and y.

Compute pairwise distances between points in the Lorentz model. Parameters ---------- x : torch.Tensor T

Compute pairwise distances between points in the Lorentz model. Parameters ---------- x : torch.Tensor T

Compute the pairwise distance between points in x and y. Parameters: x (torch.Tensor): First set of points.

Compute the Lorentzian inner product. Parameters ---------- x : torch.Tensor First tensor. y : t

Compute the cross-inner product of two points. Parameters: x (torch.Tensor): First point. y (torch.Tensor):

convert from pyg format edge_index to n by n adj matrix

Copy or inplace set from :code:`source` to :code:`dest`. A workaround to respect strides of :code:`dest` when copying :code:`source`. Th

Copy or inplace set from :code:`source` to :code:`dest`. A workaround to respect strides of :code:`dest` when copying :code:`source`. Th

Copy or inplace set from :code:`source` to :code:`dest`. A workaround to respect strides of :code:`dest` when copying :code:`source`. Th

r""" Compute geodesic distance on the Hyperboloid. .. math:: d_{\mathcal{L}}^{k}(\mathbf{x}, \mathbf{y})=\sqrt{k} \operatorname{arco

r""" Compute geodesic distance on the Hyperboloid. .. math:: d_{\mathcal{L}}^{k}(\mathbf{x}, \mathbf{y})=\sqrt{k} \operatorname{arco

r""" Compute geodesic distance on the Hyperboloid. .. math:: d_{\mathcal{L}}^{k}(\mathbf{x}, \mathbf{y})=\sqrt{k} \operatorname{arco

Compute the distance between two points on the manifold. Parameters: x (torch.Tensor): First point. y (torch

Compute the distance between two points on the manifold. Parameters: x (torch.Tensor): First point. y (torch

Compute the distance between two points on the manifold. Parameters: x (torch.Tensor): First point. y (torch

r""" Compute geodesic distance on the Hyperboloid to zero point. .. math:: Parameters ---------- x : tensor point on Hyp

r""" Compute geodesic distance on the Hyperboloid to zero point. .. math:: Parameters ---------- x : tensor point on Hyp

r""" Compute geodesic distance on the Hyperboloid to zero point. .. math:: Parameters ---------- x : tensor point on Hyp

Compute the distance from the origin to a point on the manifold. Parameters: x (torch.Tensor): Point on the manifold.

Compute the distance from the origin to a point on the manifold. Parameters: x (torch.Tensor): Point on the manifold.

Compute the distance from the origin to a point on the manifold. Parameters: x (torch.Tensor): Point on the manifold.

r""" Translate Euclidean gradient to Riemannian gradient on tangent space of :math:`x`. .. math:: \Pi_{\mathbb{R}^{d+1} \rightarrow

r""" Translate Euclidean gradient to Riemannian gradient on tangent space of :math:`x`. .. math:: \Pi_{\mathbb{R}^{d+1} \rightarrow

r""" Translate Euclidean gradient to Riemannian gradient on tangent space of :math:`x`. .. math:: \Pi_{\mathbb{R}^{d+1} \rightarrow

Convert Euclidean gradient to Riemannian gradient. Parameters: x (torch.Tensor): Point on the manifold. u (t

Convert Euclidean gradient to Riemannian gradient. Parameters: x (torch.Tensor): Point on the manifold. u (t