On the Stability of Low Pass Graph Filter with a Large Number of Edge Rewires

Recently, the stability of graph filters has been studied as one of the key theoretical properties driving the highly successful graph convolutional neural networks (GCNs). The stability of a graph filter characterizes the effect of topology perturbation on the output of a graph filter, a fundamenta...

Full description

Saved in:
Bibliographic Details
Published inICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 5568 - 5572
Main Authors Nguyen, Hoang-Son, He, Yiran, Wai, Hoi-To
Format Conference Proceeding
LanguageEnglish
Published IEEE 23.05.2022
Subjects
Online AccessGet full text

Cover

Loading…
Abstract Recently, the stability of graph filters has been studied as one of the key theoretical properties driving the highly successful graph convolutional neural networks (GCNs). The stability of a graph filter characterizes the effect of topology perturbation on the output of a graph filter, a fundamental building block for GCNs. Many existing results have focused on the regime of small perturbation with a small number of edge rewires. However, the number of edge rewires can be large in many applications. To study the latter case, this work departs from the previous analysis and proves a bound on the stability of graph filter relying on the filter's frequency response. Assuming the graph filter is low pass, we show that the stability of the filter depends on perturbation to the community structure. As an application, we show that for stochastic block model graphs, the graph filter distance converges to a small constant when the number of nodes approaches infinity. Numerical simulations validate our findings.
AbstractList Recently, the stability of graph filters has been studied as one of the key theoretical properties driving the highly successful graph convolutional neural networks (GCNs). The stability of a graph filter characterizes the effect of topology perturbation on the output of a graph filter, a fundamental building block for GCNs. Many existing results have focused on the regime of small perturbation with a small number of edge rewires. However, the number of edge rewires can be large in many applications. To study the latter case, this work departs from the previous analysis and proves a bound on the stability of graph filter relying on the filter's frequency response. Assuming the graph filter is low pass, we show that the stability of the filter depends on perturbation to the community structure. As an application, we show that for stochastic block model graphs, the graph filter distance converges to a small constant when the number of nodes approaches infinity. Numerical simulations validate our findings.
Author He, Yiran
Nguyen, Hoang-Son
Wai, Hoi-To
Author_xml – sequence: 1
  givenname: Hoang-Son
  surname: Nguyen
  fullname: Nguyen, Hoang-Son
  email: sonngh.00@link.cuhk.edu.hk
  organization: The Chinese University of Hong Kong,Shatin, Hong Kong SAR,China
– sequence: 2
  givenname: Yiran
  surname: He
  fullname: He, Yiran
  email: yrhe@se.cuhk.edu.hk
  organization: The Chinese University of Hong Kong,Shatin, Hong Kong SAR,China
– sequence: 3
  givenname: Hoi-To
  surname: Wai
  fullname: Wai, Hoi-To
  email: htwai@se.cuhk.edu.hk
  organization: The Chinese University of Hong Kong,Shatin, Hong Kong SAR,China
BookMark eNotT9tKw0AUXEXBpvoFvuwPpJ69ZbOPUtoqRFuMgm_lxN2YlTQpm0jo37tg4TDDDMMwJyFXXd85QiiDBWNgHp6Xj2W5k8JwvuAQwWipWc4uSMKyTEmIl12SGRfapMzA5w1JhuEHAHIt8xl52XZ0bBwtR6x868cT7Wta9BPd4TDQTcBjQ9e-HV2gkx8birTA8O3o6--hil4Mr2yUb27ywQ235LrGdnB3Z56Tj_XqffmUFttNXFqknoMYU2srUCC1rGpb14pbrUGgFGgMB8YRuUIZ57NKZRY1q0Smrf0S0mrFlc7EnNz_93rn3P4Y_AHDaX9-XfwBWcFO9g
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICASSP43922.2022.9747181
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library Online
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Xplore
  url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Engineering
EISBN 1665405406
9781665405409
EISSN 2379-190X
EndPage 5572
ExternalDocumentID 9747181
Genre orig-research
GroupedDBID 23M
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
ABLEC
ACGFS
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IJVOP
IPLJI
JC5
M43
OCL
RIE
RIL
RIO
RNS
ID FETCH-LOGICAL-i203t-ddb050474bfdff52d7703a43a992012aa25a41661b56da71b367ddc34d7525763
IEDL.DBID RIE
IngestDate Wed Jun 26 19:25:27 EDT 2024
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i203t-ddb050474bfdff52d7703a43a992012aa25a41661b56da71b367ddc34d7525763
PageCount 5
ParticipantIDs ieee_primary_9747181
PublicationCentury 2000
PublicationDate 2022-May-23
PublicationDateYYYYMMDD 2022-05-23
PublicationDate_xml – month: 05
  year: 2022
  text: 2022-May-23
  day: 23
PublicationDecade 2020
PublicationTitle ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
PublicationTitleAbbrev ICASSP
PublicationYear 2022
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0008748
Score 2.2568974
Snippet Recently, the stability of graph filters has been studied as one of the key theoretical properties driving the highly successful graph convolutional neural...
SourceID ieee
SourceType Publisher
StartPage 5568
SubjectTerms low pass graph filter
Low-pass filters
Numerical models
Numerical simulation
Perturbation methods
Signal processing
Stability analysis
stability of graph filter
stochastic block model
Stochastic processes
Title On the Stability of Low Pass Graph Filter with a Large Number of Edge Rewires
URI https://ieeexplore.ieee.org/document/9747181
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1bS8MwGA1zT_riZRPv5MFHu7VJmqSPMjanbHM4B3sbSZPAEFrRFtFfb77u4gUffCltadOS0J4v-c45H0KXkVCOOxMGJDEsYC61gYzSKJCKcaWo5CkDgfNwxPtTdjeLZzV0tdHCWGsr8pltwW6Vyzd5WsJSWRti3wh01lsi4Uut1uavKwWTa6ZOmLRvO9eTydijLQG1ld-s7v1RRKXCkN4uGq6fvqSOPLXKQrfSj1_GjP99vT3U_FLr4fEGh_ZRzWYHaOeb0WADDe8z7CM97EPLigz7jnOHB_kbHvvYGd-AaTXuLSBxjmFhFis8AIY4HlX1QuDirvGHDxacjV-baNrrPnb6waqQQrAgIS0CY3QYh0ww7YxzMTHCf-eKUZUkHv-JUiRWPjDjkY65USLSlAtjUsqMALNUTg9RPcsze4SwVkJTP7E1zjcntZNh6kRIoFVhZWyPUQM6Zv689MqYr_rk5O_Tp2gbBgey8YSeoXrxUtpzD_KFvqhG9xNOaaXU
link.rule.ids 309,310,780,784,789,790,796,23930,23931,25140,27925,54758
linkProvider IEEE
linkToHtml http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1bS8MwGA1jPqgvXjbxbh58tFvbpEn6KGNzajuH22BvI2kSGMIq2iH6683XXbzggy-lLW1aEtrvJN8550PoMuDSMqt9L4w19ajNjCeCLPCEpExKIlhGQeCc9lh3RO_G0biCrtZaGGNMST4zDdgtc_k6z-awVNYE7BuAznojog7nLtRa6_-u4FSsuDp-3LxtXQ8GfRdvQ9Bbuc3y7h9lVMoo0tlB6er5C_LIU2NeqEb28cua8b8vuIvqX3o93F9Hoj1UMbN9tP3NarCG0ocZdlgPO3BZ0mHfcW5xkr_hvkPP-AZsq3FnCqlzDEuzWOIEOOK4V1YMgYvb2h0-GvA2fq2jUac9bHW9ZSkFbxr6pPC0Vn7kU06V1dZGoebuS5eUyDh2CCCUMoykg2YsUBHTkgeKMK51RqjmYJfKyAGqzvKZOURYSa6Im9pq65oTygo_s9wPoVVuRGSOUA06ZvK8cMuYLPvk-O_TF2izO0yTSXLbuz9BWzBQkJsPySmqFi9zc-ZCfqHOy5H-BDvBqSc
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=proceeding&rft.title=ICASSP+2022+-+2022+IEEE+International+Conference+on+Acoustics%2C+Speech+and+Signal+Processing+%28ICASSP%29&rft.atitle=On+the+Stability+of+Low+Pass+Graph+Filter+with+a+Large+Number+of+Edge+Rewires&rft.au=Nguyen%2C+Hoang-Son&rft.au=He%2C+Yiran&rft.au=Wai%2C+Hoi-To&rft.date=2022-05-23&rft.pub=IEEE&rft.eissn=2379-190X&rft.spage=5568&rft.epage=5572&rft_id=info:doi/10.1109%2FICASSP43922.2022.9747181&rft.externalDocID=9747181