Learning Multiresolution Matrix Factorization and its Wavelet Networks on Graphs

Project

Learning Multiresolution Matrix Factorization and its Wavelet Networks on Graphs, https://arxiv.org/pdf/2111.01940.pdf.

Authors

Truong Son Hy and Risi Kondor

Requirement

• Python 3.7.10
• PyTorch 1.8.0

Recommend using Conda environment for easy installation.

General organization

• data/: Datasets.
• doc/: Documentation in \LaTeX.
• experiments/: Experiments of wavelet networks learning graphs (e.g., graph classification).
• source/: Implementation of Multiresolution Matrix Factorization (MMF) including the original (baseline), learnable and sparse; and several examples.

Please check the pdf documentation in doc/ for implementation details and usage.