descriptionPublicationkeyboard_double_arrow_right Article , Preprint , Conference object 23 May 2022Embargo end date: 01 Jan 2021Publisher:IEEEJournal:ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

Authors: Yang, M. (author); Isufi, E. (author); Leus, G.J.T. (author);

doi: 10.1109/icassp43922.2022.9746017 , 10.48550/arxiv.2110.02585

arXiv: http://arxiv.org/abs/2110.02585

Simplicial Convolutional Neural Networks

- Summary
- Subjects
- Metrics

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.

5 Pages, 2 figures, 1 table, submitted to ICASSP 2022

Related Organizations

Delft University of Technology
Netherlands

Keywords

Signal Processing (eess.SP), FOS: Computer and information sciences, Computer Science - Machine Learning, simplicial neural network, FOS: Electrical engineering, electronic engineering, information engineering, Hodge Laplacian, Simplicial complex, Electrical Engineering and Systems Science - Signal Processing, simplicial filter, Machine Learning (cs.LG)

Impact byBIP!

	citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	20
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Top 10%
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Top 10%
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Top 10%