Journal
APPLIED AND COMPUTATIONAL HARMONIC ANALYSIS
Volume 49, Issue 3, Pages 1046-1074Publisher
ACADEMIC PRESS INC ELSEVIER SCIENCE
DOI: 10.1016/j.acha.2019.06.003
Keywords
Scattering transform; Graph neural networks; Graph convolution; Spectral graph theory; Wavelets; Permutation invariance; Feature learning
Categories
Funding
- NSF [DMS-14-18386, DMS-18-21266, DMS-18-30418]
- NGA
- NSF
Ask authors/readers for more resources
We generalize the scattering transform to graphs and consequently construct a convolutional neural network on graphs. We show that under certain conditions, any feature generated by such a network is approximately invariant to permutations and stable to signal and graph manipulations. Numerical results demonstrate competitive performance on relevant datasets. (C) 2019 Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available