Bridging the Gap Between Spectral and Spatial Domains in Graph Neural
Networks
- URL: http://arxiv.org/abs/2003.11702v1
- Date: Thu, 26 Mar 2020 01:49:24 GMT
- Title: Bridging the Gap Between Spectral and Spatial Domains in Graph Neural
Networks
- Authors: Muhammet Balcilar, Guillaume Renton, Pierre Heroux, Benoit Gauzere,
Sebastien Adam, Paul Honeine
- Abstract summary: We show some equivalence of the graph convolution process regardless it is designed in the spatial or the spectral domain.
The proposed framework is used to design new convolutions in spectral domain with a custom frequency profile while applying them in the spatial domain.
- Score: 8.563354084119062
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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
Related papers
- HoloNets: Spectral Convolutions do extend to Directed Graphs [59.851175771106625]
Conventional wisdom dictates that spectral convolutional networks may only be deployed on undirected graphs.
Here we show this traditional reliance on the graph Fourier transform to be superfluous.
We provide a frequency-response interpretation of newly developed filters, investigate the influence of the basis used to express filters and discuss the interplay with characteristic operators on which networks are based.
arXiv Detail & Related papers (2023-10-03T17:42:09Z) - Geometric Graph Filters and Neural Networks: Limit Properties and
Discriminability Trade-offs [122.06927400759021]
We study the relationship between a graph neural network (GNN) and a manifold neural network (MNN) when the graph is constructed from a set of points sampled from the manifold.
We prove non-asymptotic error bounds showing that convolutional filters and neural networks on these graphs converge to convolutional filters and neural networks on the continuous manifold.
arXiv Detail & Related papers (2023-05-29T08:27:17Z) - Specformer: Spectral Graph Neural Networks Meet Transformers [51.644312964537356]
Spectral graph neural networks (GNNs) learn graph representations via spectral-domain graph convolutions.
We introduce Specformer, which effectively encodes the set of all eigenvalues and performs self-attention in the spectral domain.
By stacking multiple Specformer layers, one can build a powerful spectral GNN.
arXiv Detail & Related papers (2023-03-02T07:36:23Z) - Quasi-Framelets: Another Improvement to GraphNeural Networks [29.689868950666117]
spectral graph neural networks (GNNs) improve graph learning task performance via proposing various spectral filters in spectral domain to capture both global and local graph structure information.
Our new framelets convolution incorporates the filtering func-tions directly designed in the spectral domain to overcome these limitations.
The proposed convolution shows a great flexibility in cutting-off spectral information and effectively mitigate the negative effect of noisy graph signals.
arXiv Detail & Related papers (2022-01-11T00:10:28Z) - Spectral Graph Convolutional Networks With Lifting-based Adaptive Graph
Wavelets [81.63035727821145]
Spectral graph convolutional networks (SGCNs) have been attracting increasing attention in graph representation learning.
We propose a novel class of spectral graph convolutional networks that implement graph convolutions with adaptive graph wavelets.
arXiv Detail & Related papers (2021-08-03T17:57:53Z) - Spectral-Spatial Global Graph Reasoning for Hyperspectral Image
Classification [50.899576891296235]
Convolutional neural networks have been widely applied to hyperspectral image classification.
Recent methods attempt to address this issue by performing graph convolutions on spatial topologies.
arXiv Detail & Related papers (2021-06-26T06:24:51Z) - Graph Networks with Spectral Message Passing [1.0742675209112622]
We introduce the Spectral Graph Network, which applies message passing to both the spatial and spectral domains.
Our results show that the Spectral GN promotes efficient training, reaching high performance with fewer training iterations despite having more parameters.
arXiv Detail & Related papers (2020-12-31T21:33:17Z) - An Experimental Study of the Transferability of Spectral Graph Networks [5.736353542430439]
Spectral graph convolutional networks are generalizations of standard convolutional networks for graph-structured data using the Laplacian operator.
Recent works have proved the stability of spectral filters under graph benchmarks.
arXiv Detail & Related papers (2020-12-18T14:15:07Z) - Graphon Pooling in Graph Neural Networks [169.09536309161314]
Graph neural networks (GNNs) have been used effectively in different applications involving the processing of signals on irregular structures modeled by graphs.
We propose a new strategy for pooling and sampling on GNNs using graphons which preserves the spectral properties of the graph.
arXiv Detail & Related papers (2020-03-03T21:04:20Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.