CayleyNets : graph convolutional neural networks with complex rational spectral filters
The rise of graph-structured data such as social networks, regulatory networks, citation graphs, and functional brain networks, in combination with resounding success of deep learning in various applications, has brought the interest in generalizing deep learning models to non-Euclidean domains. In...
Saved in:
Main Authors: | , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/139445 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-139445 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1394452020-08-06T01:11:12Z CayleyNets : graph convolutional neural networks with complex rational spectral filters Levie, Ron Monti, Federico Bresson, Xavier Bronstein, Michael M. School of Computer Science and Engineering Data Science and AI Center Engineering::Computer science and engineering Geometric Deep Learning Graph Convolution Neural Networks The rise of graph-structured data such as social networks, regulatory networks, citation graphs, and functional brain networks, in combination with resounding success of deep learning in various applications, has brought the interest in generalizing deep learning models to non-Euclidean domains. In this paper, we introduce a new spectral domain convolutional architecture for deep learning on graphs. The core ingredient of our model is a new class of parametric rational complex functions (Cayley polynomials) allowing to efficiently compute spectral filters on graphs that specialize on frequency bands of interest. Our model generates rich spectral filters that are localized in space, scales linearly with the size of the input data for sparsely connected graphs, and can handle different constructions of Laplacian operators. Extensive experimental results show the superior performance of our approach, in comparison to other spectral domain convolutional architectures, on spectral image classification, community detection, vertex classification, and matrix completion tasks. Accepted version The work of F. Monti and M. M. Bronstein was supported inpart by the ERC Consolidator Grant 724228 (LEMAN), in part by the GoogleFaculty Research Awards, in part by the Amazon AWS ML Research Award,in part by the Royal Society Wolfson Research Merit Award, and in part by theRudolf Diesel fellowship at the Institute for Advanced Studies, TU Munich. Thework of X. Bresson was supported by the NRF Fellowship NRFF2017-10. 2020-05-19T08:32:54Z 2020-05-19T08:32:54Z 2018 Journal Article Levie, R., Monti, F., Bresson, X., & Bronstein, M. M. (2019). CayleyNets : graph convolutional neural networks with complex rational spectral filters. IEEE Transactions on Signal Processing, 67(1), 97-109. doi:10.1109/tsp.2018.2879624 1053-587X https://hdl.handle.net/10356/139445 10.1109/TSP.2018.2879624 2-s2.0-85056170412 1 67 97 109 en IEEE Transactions on Signal Processing © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TSP.2018.2879624 application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
country |
Singapore |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Geometric Deep Learning Graph Convolution Neural Networks |
spellingShingle |
Engineering::Computer science and engineering Geometric Deep Learning Graph Convolution Neural Networks Levie, Ron Monti, Federico Bresson, Xavier Bronstein, Michael M. CayleyNets : graph convolutional neural networks with complex rational spectral filters |
description |
The rise of graph-structured data such as social networks, regulatory networks, citation graphs, and functional brain networks, in combination with resounding success of deep learning in various applications, has brought the interest in generalizing deep learning models to non-Euclidean domains. In this paper, we introduce a new spectral domain convolutional architecture for deep learning on graphs. The core ingredient of our model is a new class of parametric rational complex functions (Cayley polynomials) allowing to efficiently compute spectral filters on graphs that specialize on frequency bands of interest. Our model generates rich spectral filters that are localized in space, scales linearly with the size of the input data for sparsely connected graphs, and can handle different constructions of Laplacian operators. Extensive experimental results show the superior performance of our approach, in comparison to other spectral domain convolutional architectures, on spectral image classification, community detection, vertex classification, and matrix completion tasks. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Levie, Ron Monti, Federico Bresson, Xavier Bronstein, Michael M. |
format |
Article |
author |
Levie, Ron Monti, Federico Bresson, Xavier Bronstein, Michael M. |
author_sort |
Levie, Ron |
title |
CayleyNets : graph convolutional neural networks with complex rational spectral filters |
title_short |
CayleyNets : graph convolutional neural networks with complex rational spectral filters |
title_full |
CayleyNets : graph convolutional neural networks with complex rational spectral filters |
title_fullStr |
CayleyNets : graph convolutional neural networks with complex rational spectral filters |
title_full_unstemmed |
CayleyNets : graph convolutional neural networks with complex rational spectral filters |
title_sort |
cayleynets : graph convolutional neural networks with complex rational spectral filters |
publishDate |
2020 |
url |
https://hdl.handle.net/10356/139445 |
_version_ |
1681057784008802304 |