InfoGain Wavelets: Furthering the Design of Graph Diffusion Wavelets
This work addresses a specific bottleneck in graph signal processing for researchers in machine learning, but it appears incremental as it builds on existing wavelet and GNN frameworks.
The authors tackled the problem of selecting diffusion scales in graph diffusion wavelets by proposing an unsupervised method based on information theory, and demonstrated its effectiveness by incorporating it into wavelet-based GNNs for graph classification experiments.
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, these scales are chosen to be dyadic integers, $2^j$. 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, which are modeled after the geometric scattering transform, via graph classification experiments.