Search Results for author:
Found 2 papers, 1 papers with code
Pointspectrum: Equivariance Meets Laplacian Filtering for Graph Representation Learning
In a different GRL approach, spectral methods based on graph filtering have emerged addressing over smoothing; however, up to now, they employ traditional neural networks that cannot efficiently exploit the structure of graph data.
What training reveals about neural network complexity
This work explores the Benevolent Training Hypothesis (BTH) which argues that the complexity of the function a deep neural network (NN) is learning can be deduced by its training dynamics.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
