SPLGAug 2, 2019

An Underparametrized Deep Decoder Architecture for Graph Signals

arXiv:1908.00878v28 citations
AI Analysis

This addresses the challenge of applying deep learning to non-grid data like graphs, offering a domain-specific solution for graph signal processing.

The paper tackles the problem of reconstructing signals on irregular graph-structured domains by generalizing untrained, underparametrized deep architectures to incorporate graph topology through hierarchical clustering-based upsampling, resulting in drastically improved reconstruction performance on synthetic and real-world datasets.

While deep convolutional architectures have achieved remarkable results in a gamut of supervised applications dealing with images and speech, recent works show that deep untrained non-convolutional architectures can also outperform state-of-the-art methods in several tasks such as image compression and denoising. Motivated by the fact that many contemporary datasets have an irregular structure different from a 1D/2D grid, this paper generalizes untrained and underparametrized non-convolutional architectures to signals defined over irregular domains represented by graphs. The proposed architecture consists of a succession of layers, each of them implementing an upsampling operator, a linear feature combination, and a scalar nonlinearity. A novel element is the incorporation of upsampling operators accounting for the structure of the supporting graph, which is achieved by considering a systematic graph coarsening approach based on hierarchical clustering. The numerical results carried out in synthetic and real-world datasets showcase that the reconstruction performance can improve drastically if the information of the supporting graph topology is taken into account.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes