Simplicial Convolutional Neural Networks

Maosheng Yang; Elvin Isufi; Geert Leus

doi:10.1109/ICASSP43922.2022.9746017

Simplicial Convolutional Neural Networks

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

7 Citations (Scopus)

15 Downloads (Pure)

Abstract

Graphs can model networked data by representing them as nodes and their pairwise relationships as edges. Recently, signal processing and neural networks have been extended to process and learn from data on graphs, with achievements in tasks like graph signal reconstruction, graph or node classifications, and link prediction. However, these methods are only suitable for data defined on the nodes of a graph. In this paper, we propose a simplicial convolutional neural network (SCNN) architecture to learn from data defined on simplices, e.g., nodes, edges, triangles, etc. We study the SCNN permutation and orientation equivariance, complexity, and spectral analysis. Finally, we test the SCNN performance for imputing citations on a coauthorship complex.

Original language	English
Title of host publication	Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Place of Publication	Piscataway
Publisher	IEEE
Pages	8847-8851
Number of pages	5
ISBN (Electronic)	978-1-6654-0540-9
ISBN (Print)	978-1-6654-0541-6
DOIs	https://doi.org/10.1109/ICASSP43922.2022.9746017
Publication status	Published - 2022
Event	ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Singapore, Singapore Duration: 23 May 2022 → 27 May 2022

Conference

Conference	ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Country/Territory	Singapore
City	Singapore
Period	23/05/22 → 27/05/22

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care

Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Simplicial complex
Hodge Laplacian
simplicial filter
simplicial neural network

Access to Document

10.1109/ICASSP43922.2022.9746017

Simplicial_Convolutional_Neural_NetworksFinal published version, 1.05 MB

Cite this

@inproceedings{53f1da58abee48349822cce691900b18,

title = "Simplicial Convolutional Neural Networks",

abstract = "Graphs can model networked data by representing them as nodes and their pairwise relationships as edges. Recently, signal processing and neural networks have been extended to process and learn from data on graphs, with achievements in tasks like graph signal reconstruction, graph or node classifications, and link prediction. However, these methods are only suitable for data defined on the nodes of a graph. In this paper, we propose a simplicial convolutional neural network (SCNN) architecture to learn from data defined on simplices, e.g., nodes, edges, triangles, etc. We study the SCNN permutation and orientation equivariance, complexity, and spectral analysis. Finally, we test the SCNN performance for imputing citations on a coauthorship complex.",

keywords = "Simplicial complex, Hodge Laplacian, simplicial filter, simplicial neural network",

author = "Maosheng Yang and Elvin Isufi and Geert Leus",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) ; Conference date: 23-05-2022 Through 27-05-2022",

year = "2022",

doi = "10.1109/ICASSP43922.2022.9746017",

language = "English",

isbn = "978-1-6654-0541-6",

pages = "8847--8851",

booktitle = "Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)",

publisher = "IEEE",

address = "United States",

}

Yang, M , Isufi, E & Leus, G 2022, Simplicial Convolutional Neural Networks. in Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)., 9746017, IEEE, Piscataway, pp. 8847-8851, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, Singapore, 23/05/22. https://doi.org/10.1109/ICASSP43922.2022.9746017

Simplicial Convolutional Neural Networks. / Yang, Maosheng ; Isufi, Elvin ; Leus, Geert.
Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Piscataway: IEEE, 2022. p. 8847-8851 9746017.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Simplicial Convolutional Neural Networks

AU - Yang, Maosheng

AU - Isufi, Elvin

AU - Leus, Geert

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2022

Y1 - 2022

N2 - Graphs can model networked data by representing them as nodes and their pairwise relationships as edges. Recently, signal processing and neural networks have been extended to process and learn from data on graphs, with achievements in tasks like graph signal reconstruction, graph or node classifications, and link prediction. However, these methods are only suitable for data defined on the nodes of a graph. In this paper, we propose a simplicial convolutional neural network (SCNN) architecture to learn from data defined on simplices, e.g., nodes, edges, triangles, etc. We study the SCNN permutation and orientation equivariance, complexity, and spectral analysis. Finally, we test the SCNN performance for imputing citations on a coauthorship complex.

AB - Graphs can model networked data by representing them as nodes and their pairwise relationships as edges. Recently, signal processing and neural networks have been extended to process and learn from data on graphs, with achievements in tasks like graph signal reconstruction, graph or node classifications, and link prediction. However, these methods are only suitable for data defined on the nodes of a graph. In this paper, we propose a simplicial convolutional neural network (SCNN) architecture to learn from data defined on simplices, e.g., nodes, edges, triangles, etc. We study the SCNN permutation and orientation equivariance, complexity, and spectral analysis. Finally, we test the SCNN performance for imputing citations on a coauthorship complex.

KW - Simplicial complex

KW - Hodge Laplacian

KW - simplicial filter

KW - simplicial neural network

UR - http://www.scopus.com/inward/record.url?scp=85131254983&partnerID=8YFLogxK

U2 - 10.1109/ICASSP43922.2022.9746017

DO - 10.1109/ICASSP43922.2022.9746017

M3 - Conference contribution

SN - 978-1-6654-0541-6

SP - 8847

EP - 8851

BT - Proceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

PB - IEEE

CY - Piscataway

T2 - ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Y2 - 23 May 2022 through 27 May 2022

ER -

Simplicial Convolutional Neural Networks

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this