Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks

03/26/2020
by   Muhammet Balcilar, et al.
4

This paper aims at revisiting Graph Convolutional Neural Networks by bridging the gap between spectral and spatial design of graph convolutions. We theoretically demonstrate some equivalence of the graph convolution process regardless it is designed in the spatial or the spectral domain. The obtained general framework allows to lead a spectral analysis of the most popular ConvGNNs, explaining their performance and showing their limits. Moreover, the proposed framework is used to design new convolutions in spectral domain with a custom frequency profile while applying them in the spatial domain. We also propose a generalization of the depthwise separable convolution framework for graph convolutional networks, what allows to decrease the total number of trainable parameters by keeping the capacity of the model. To the best of our knowledge, such a framework has never been used in the GNNs literature. Our proposals are evaluated on both transductive and inductive graph learning problems. Obtained results show the relevance of the proposed method and provide one of the first experimental evidence of transferability of spectral filter coefficients from one graph to another. Our source codes are publicly available at: https://github.com/balcilar/Spectral-Designed-Graph-Convolutions

READ FULL TEXT

page 8

page 10

research
04/17/2020

Bridging the Gap Between Spectral and Spatial Domainsin Graph Neural Networks

Bridging the Gap Between Spectral and Spatial Domainsin Graph Neural Net...
research
05/31/2023

Spectral Heterogeneous Graph Convolutions via Positive Noncommutative Polynomials

Heterogeneous Graph Neural Networks (HGNNs) have gained significant popu...
research
07/30/2019

Transferability of Spectral Graph Convolutional Neural Networks

This paper focuses on spectral graph convolutional neural networks (Conv...
research
05/04/2021

Multipath Graph Convolutional Neural Networks

Graph convolution networks have recently garnered a lot of attention for...
research
04/26/2021

Graph Neural Networks with Adaptive Frequency Response Filter

Graph Neural Networks have recently become a prevailing paradigm for var...
research
05/21/2021

Dynamic Filters in Graph Convolutional Neural Networks

Over the last few years, we have seen increasing data generated from non...
research
08/15/2018

Modelling Irregular Spatial Patterns using Graph Convolutional Neural Networks

The understanding of geographical reality is a process of data represent...

Please sign up or login with your details

Forgot password? Click here to reset