×
We propose approaches based on Laplacian eigenmaps to enhance the common-used cross-entropy loss, called LEELoss.
Given this situation, we concentrate on the standard loss function of those works to realize whether enhancing the objective function can facilitate the graph.
This study shows that utilizing the Laplacian eigenmaps as a regularizer in the original loss function can further enhance the performance of the ...
Training graph classifiers able to distinguish between healthy brains and dysfunctional ones, can help identifying substructures associated to specific ...
Connected Papers is a visual tool to help researchers and applied scientists find academic papers relevant to their field of work.
Oct 7, 2024 · Enhancing framelet GCNs with generalized p-Laplacian ... Enhanced Loss Function based on Laplacian Eigenmaps for Graph Classification.
Oct 31, 2022 · Summary: The paper proposes a novel objective for graph embedding, called Generalized Laplacian EigeNmaps (GLEN), to learn graph representation ...
We had previously proposed a supervised Laplacian eigenmap for visualization (SLE-ML) that can handle multi-label data.
Laplacian Eigenmaps [3] and IsoMap [32] are graph embedding methods that reduce the dimension- ality of data by assuming the data exists on a low-dimensional ...
People also ask
Feb 29, 2008 · The non-linear mapping by LE is related to spectral clustering and allows an effective way to learn the parameters of the weight matrix for LE ...