Efficient and Stable Graph Scattering Transforms via Pruning

01/27/2020
by   Vassilis N. Ioannidis, et al.
0

Graph convolutional networks (GCNs) have well-documented performance in various graph learning tasks, but their analysis is still at its infancy. Graph scattering transforms (GSTs) offer training-free deep GCN models that extract features from graph data, and are amenable to generalization and stability analyses. The price paid by GSTs is exponential complexity in space and time that increases with the number of layers. This discourages deployment of GSTs when a deep architecture is needed. The present work addresses the complexity limitation of GSTs by introducing an efficient so-termed pruned (p)GST approach. The resultant pruning algorithm is guided by a graph-spectrum-inspired criterion, and retains informative scattering features on-the-fly while bypassing the exponential complexity associated with GSTs. Stability of the novel pGSTs is also established when the input graph data or the network structure are perturbed. Furthermore, the sensitivity of pGST to random and localized signal perturbations is investigated analytically and experimentally. Numerical tests showcase that pGST performs comparably to the baseline GST at considerable computational savings. Furthermore, pGST achieves comparable performance to state-of-the-art GCNs in graph and 3D point cloud classification tasks. Upon analyzing the pGST pruning patterns, it is shown that graph data in different domains call for different network architectures, and that the pruning algorithm may be employed to guide the design choices for contemporary GCNs.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/11/2019

Stability of Graph Scattering Transforms

Scattering transforms are non-trainable deep convolutional architectures...
research
01/26/2023

Graph Scattering beyond Wavelet Shackles

This work develops a flexible and mathematically sound framework for the...
research
10/07/2018

Graph Classification with Geometric Scattering

One of the most notable contributions of deep learning is the applicatio...
research
06/22/2018

Diffusion Scattering Transforms on Graphs

Stability is a key aspect of data analysis. In many applications, the na...
research
03/18/2020

Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks

Graph convolutional networks (GCNs) have shown promising results in proc...
research
10/06/2020

Data-Driven Learning of Geometric Scattering Networks

Graph neural networks (GNNs) in general, and graph convolutional network...
research
05/30/2023

Budget-Aware Graph Convolutional Network Design using Probabilistic Magnitude Pruning

Graph convolutional networks (GCNs) are nowadays becoming mainstream in ...

Please sign up or login with your details

Forgot password? Click here to reset