Enhancing Geometric Deep Learning via Graph Filter Deconvolution
arXiv:1810.00661
Abstract
In this paper, we incorporate a graph filter deconvolution step into the classical geometric convolutional neural network pipeline. More precisely, under the assumption that the graph domain plays a role in the generation of the observed graph signals, we pre-process every signal by passing it through a sparse deconvolution operation governed by a pre-specified filter bank. This deconvolution operation is formulated as a group-sparse recovery problem, and convex relaxations that can be solved efficiently are put forth. The deconvolved signals are then fed into the geometric convolutional neural network, yielding better classification performance than their unprocessed counterparts. Numerical experiments showcase the effectiveness of the deconvolution step on classification tasks on both synthetic and real-world settings.
arXiv comment5 pages, 8 figures, to appear in the proceedings of the 2018 6th IEEE Global Conference on Signal and Information Processing, November 26-29, 2018, Anaheim, California, USA
References in corpus (13)
- Semi-Supervised Classification with Graph Convolutional Networks
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Geometric deep learning: going beyond Euclidean data
- Spectral Networks and Locally Connected Networks on Graphs
- Discrete Signal Processing on Graphs
- Discrete Signal Processing on Graphs: Sampling Theory
- Convolutional Neural Network Architectures for Signals Supported on Graphs
- Sampling of graph signals with successive local aggregations
- Stationary signal processing on graphs
- Stationary Graph Processes and Spectral Estimation
- Kernel-based Reconstruction of Graph Signals
- Reconstruction of Graph Signals through Percolation from Seeding Nodes
- Blind Identification of Invertible Graph Filters with Multiple Sparse Inputs