COSIE.loss.crossview_contrastive_Loss

crossview_contrastive_Loss(view1, view2, gamma=9.0, EPS=2.220446049250313e-16)

Compute the cross-view contrastive loss between two embedding views.

Parameters

view1torch.Tensor

A tensor of shape (n_cells, dim) representing the first view’s features.

view2torch.Tensor

A tensor of shape (n_cells, dim) representing the second view’s features. Must be the same shape as view1.

gammafloat, optional

The weight applied to the entropy regularization term. Default is 9.0.

EPSfloat, optional

A small constant used to avoid \(\log(0)\). Required for numerical stability. Default is sys.float_info.epsilon.

Returns

losstorch.Tensor

A scalar tensor representing the contrastive loss.