Sorry, you need to enable JavaScript to visit this website.

Untrained graph neural networks for denoising

Citation Author(s):
Samuel Rey, Santiago Segarra, Reinhard Heckel, Antonio G. Marques
Submitted by:
Samuel Rey
Last updated:
29 May 2023 - 4:53am
Document Type:
Poster
Document Year:
2023
Event:
Presenters:
Samuel Rey
Paper Code:
MLSP-P2.5
 

A fundamental problem in signal processing is to denoise a signal. While there are many well-performing methods for denoising signals defined on regular domains, including images defined on a two-dimensional pixel grid, many important classes of signals are defined over irregular domains that can be conveniently represented by a graph. This paper introduces two untrained graph neural network architectures for graph signal denoising, develops theoretical guarantees for their denoising capabilities in a simple setup, and provides empirical evidence in more general scenarios. The two architectures differ on how they incorporate the information encoded in the graph, with one relying on graph convolutions and the other employing graph upsampling operators based on hierarchical clustering. Each architecture implements a different prior over the targeted signals. Finally, we provide numerical experiments with synthetic and real datasets that i) asses the denoising behavior predicted by our theoretical results and ii) compare the denoising performance of our architectures with that of existing alternatives.

up
1 user has voted: Andrei Buciulea