Spectral Convergence of Complexon Shift Operators

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhang, Purui, Jian, Xingchao, Ji, Feng, Tay, Wee Peng, Wen, Bihan
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909188876140544
author Zhang, Purui
Jian, Xingchao
Ji, Feng
Tay, Wee Peng
Wen, Bihan
author_facet Zhang, Purui
Jian, Xingchao
Ji, Feng
Tay, Wee Peng
Wen, Bihan
contents Topological Signal Processing (TSP) utilizes simplicial complexes to model structures with higher order than vertices and edges. In this paper, we study the transferability of TSP via a generalized higher-order version of graphon, known as complexon. We recall the notion of a complexon as the limit of a simplicial complex sequence [1]. Inspired by the graphon shift operator and message-passing neural network, we construct a marginal complexon and complexon shift operator (CSO) according to components of all possible dimensions from the complexon. We investigate the CSO's eigenvalues and eigenvectors and relate them to a new family of weighted adjacency matrices. We prove that when a simplicial complex signal sequence converges to a complexon signal, the eigenvalues, eigenspaces, and Fourier transform of the corresponding CSOs converge to that of the limit complexon signal. This conclusion is further verified by two numerical experiments. These results hint at learning transferability on large simplicial complexes or simplicial complex sequences, which generalize the graphon signal processing framework.
format Preprint
id arxiv_https___arxiv_org_abs_2309_07169
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Spectral Convergence of Complexon Shift Operators
Zhang, Purui
Jian, Xingchao
Ji, Feng
Tay, Wee Peng
Wen, Bihan
Signal Processing
Machine Learning
Topological Signal Processing (TSP) utilizes simplicial complexes to model structures with higher order than vertices and edges. In this paper, we study the transferability of TSP via a generalized higher-order version of graphon, known as complexon. We recall the notion of a complexon as the limit of a simplicial complex sequence [1]. Inspired by the graphon shift operator and message-passing neural network, we construct a marginal complexon and complexon shift operator (CSO) according to components of all possible dimensions from the complexon. We investigate the CSO's eigenvalues and eigenvectors and relate them to a new family of weighted adjacency matrices. We prove that when a simplicial complex signal sequence converges to a complexon signal, the eigenvalues, eigenspaces, and Fourier transform of the corresponding CSOs converge to that of the limit complexon signal. This conclusion is further verified by two numerical experiments. These results hint at learning transferability on large simplicial complexes or simplicial complex sequences, which generalize the graphon signal processing framework.
title Spectral Convergence of Complexon Shift Operators
topic Signal Processing
Machine Learning
url https://arxiv.org/abs/2309.07169