Simplicial Convolutional Neural Networks

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

7 Citations (Scopus)
12 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 languageEnglish
Title of host publicationProceedings of the ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Place of PublicationPiscataway
PublisherIEEE
Pages8847-8851
Number of pages5
ISBN (Electronic)978-1-6654-0540-9
ISBN (Print)978-1-6654-0541-6
DOIs
Publication statusPublished - 2022
EventICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) - Singapore, Singapore
Duration: 23 May 202227 May 2022

Conference

ConferenceICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Country/TerritorySingapore
CitySingapore
Period23/05/2227/05/22

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

Fingerprint

Dive into the research topics of 'Simplicial Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this