Goto

Collaborating Authors

 infogain wavelet

InfoGain Wavelets: Furthering the Design of Diffusion Wavelets for Graph-Structured Data

Johnson, David R., Krishnaswamy, Smita, Perlmutter, Michael

arXiv.org Machine Learning

Diffusion wavelets extract information from graph signals at different scales of resolution by utilizing graph diffusion operators raised to various powers, known as diffusion scales. Traditionally, the diffusion scales are chosen to be dyadic integers, $\mathbf{2^j}$. Here, we propose a novel, unsupervised method for selecting the diffusion scales based on ideas from information theory. We then show that our method can be incorporated into wavelet-based GNNs via graph classification experiments.

2504.08802
  Country:
  Genre: Research Report > New Finding (0.67)
  Industry:
  Technology:

Add feedback