Skip to content

Pooling implementation question: weighted sum of manifold embeddings in Eq.(8) #6

Description

@zhangyu2234

Hello,

Thank you for your excellent work on CUSP. I am currently implementing the pooling module described in Eq. (6)–(8) and I have a question regarding the filter-level aggregation step.

In my implementation, after the component-level attention fusion, each filter produces an embedding ζ^(l), which is still represented on the product manifold (each component lies on its corresponding stereographic manifold). Then the paper defines the final embedding as

ζ = sum_{l=1}^L ε_l ζ^(l)

which I implemented as

zeta_l_tensor = torch.stack(zeta_l_list, dim=0)   # (L, N, D)
epsilon = softmax(self.epsilon)
zeta = torch.sum(epsilon.view(L,1,1) * zeta_l_tensor, dim=0)

However, this operation is a standard Euclidean weighted sum, while ζ^(l) are still manifold-valued embeddings.
So this seems to perform linear combination directly in the ambient space rather than on the manifold.

My question is:

Should the filter-level aggregation be done in the tangent space (e.g., using logmap0 before summation and optionally expmap0 after), or is it intended that ζ^(l) are already treated as Euclidean features at this stage?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions