Back to Search
Start Over
Graph matching as a graph convolution operator for graph neural networks
- Source :
- Pattern Recognition Letters, Pattern Recognition Letters, Elsevier, 2021, pp.59-66. ⟨10.1016/j.patrec.2021.06.008⟩
- Publication Year :
- 2021
- Publisher :
- HAL CCSD, 2021.
-
Abstract
- Convolutional neural networks (CNNs), in a few decades, have outperformed the existing state of the art methods in classification context. However, in the way they were formalised, CNNs are bound to operate on euclidean spaces. Indeed, convolution is a signal operation that are defined on euclidean spaces. This has restricted deep learning main use to euclidean-defined data such as sound or image. And yet, numerous computer application fields (among which network analysis, computational social science, chemo-informatics or computer graphics) induce non-euclideanly defined data such as graphs, networks or manifolds. In this paper we propose a new convolution neural network architecture, defined directly into graph space. Convolution and pooling operators are defined in graph domain thanks to a graph matching procedure between the input signal and a filter. We show its usability in a back-propagation context. Experimental results show that our model performance is at state of the art level on simple tasks. It shows robustness with respect to graph domain changes and improvement with respect to other euclidean and non-euclidean convolutional architectures.
- Subjects :
- Theoretical computer science
Computer science
Context (language use)
02 engineering and technology
01 natural sciences
Convolutional neural network
Convolution
Computer graphics
Artificial Intelligence
Robustness (computer science)
0103 physical sciences
0202 electrical engineering, electronic engineering, information engineering
010306 general physics
ComputingMilieux_MISCELLANEOUS
business.industry
Deep learning
[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]
Filter (signal processing)
[INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV]
Signal Processing
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
business
Software
Network analysis
Subjects
Details
- Language :
- English
- ISSN :
- 01678655
- Database :
- OpenAIRE
- Journal :
- Pattern Recognition Letters, Pattern Recognition Letters, Elsevier, 2021, pp.59-66. ⟨10.1016/j.patrec.2021.06.008⟩
- Accession number :
- edsair.doi.dedup.....5d146a03863dd088f054553d227650d1