CogniSNN: A First Exploration to Random Graph Architecture based Spiking Neural Networks with Enhanced Expandability and Neuroplasticity Article Swipe

PDF

Yongsheng Huang , Peibo Duan , Kai Sun , Changsheng Zhang , Bin Zhang , Mingkun Xu ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2505.05992

Despite advances in spiking neural networks (SNNs) in numerous tasks, their architectures remain highly similar to traditional artificial neural networks (ANNs), restricting their ability to mimic natural connections between biological neurons. This paper develops a new modeling paradigm for SNN with random graph architecture (RGA), termed Cognition-aware SNN (CogniSNN). Furthermore, we improve the expandability and neuroplasticity of CogniSNN by introducing a modified spiking residual neural node (ResNode) to counteract network degradation in deeper graph pathways, as well as a critical path-based algorithm that enables CogniSNN to perform continual learning on new tasks leveraging the features of the data and the RGA learned in the old task. Experiments show that CogniSNN with re-designed ResNode performs outstandingly in neuromorphic datasets with fewer parameters, achieving 95.5% precision in the DVS-Gesture dataset with only 5 timesteps. The critical path-based approach decreases 3% to 5% forgetting while maintaining expected performance in learning new tasks that are similar to or distinct from the old ones. This study showcases the potential of RGA-based SNN and paves a new path for biologically inspired networks based on graph theory.

Related Topics

Exploration Of North America

Georgie & Mandy's First Marriage

First Contact (Anthropology)

First Light (Astronomy)

From First To Last

First Amendment To The United States Constitution

The First Law

First Congo War

First Lady Of The United States

First Impeachment Of Donald Trump

First Nagorno-Karabakh War

First Language

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2505.05992
PDF: https://arxiv.org/pdf/2505.05992
OA Status: green
OpenAlex ID: https://openalex.org/W4417085843

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4417085843

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2505.05992

Digital Object Identifier
Title: CogniSNN: A First Exploration to Random Graph Architecture based Spiking Neural Networks with Enhanced Expandability and Neuroplasticity

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-05-09

Full publication date if available
Authors: Yongsheng Huang, Peibo Duan, Kai Sun, Changsheng Zhang, Bin Zhang, Mingkun Xu

List of authors in order
Landing page: https://arxiv.org/abs/2505.05992

Publisher landing page
PDF URL: https://arxiv.org/pdf/2505.05992

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2505.05992

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4417085843
doi	https://doi.org/10.48550/arxiv.2505.05992
ids.doi	https://doi.org/10.48550/arxiv.2505.05992
ids.openalex	https://openalex.org/W4417085843
fwci
type	preprint
title	CogniSNN: A First Exploration to Random Graph Architecture based Spiking Neural Networks with Enhanced Expandability and Neuroplasticity
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	pmh:oai:arXiv.org:2505.05992
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S4306400194
locations[0].source.issn
locations[0].source.type	repository
locations[0].source.is_oa	True
locations[0].source.issn_l
locations[0].source.is_core	False
locations[0].source.is_in_doaj	False
locations[0].source.display_name	arXiv (Cornell University)
locations[0].source.host_organization	https://openalex.org/I205783295
locations[0].source.host_organization_name	Cornell University
locations[0].source.host_organization_lineage	https://openalex.org/I205783295
locations[0].license
locations[0].pdf_url	https://arxiv.org/pdf/2505.05992
locations[0].version	submittedVersion
locations[0].raw_type	text
locations[0].license_id
locations[0].is_accepted	False
locations[0].is_published	False
locations[0].raw_source_name
locations[0].landing_page_url	http://arxiv.org/abs/2505.05992
locations[1].id	doi:10.48550/arxiv.2505.05992
locations[1].is_oa	True
locations[1].source.id	https://openalex.org/S4306400194
locations[1].source.issn
locations[1].source.type	repository
locations[1].source.is_oa	True
locations[1].source.issn_l
locations[1].source.is_core	False
locations[1].source.is_in_doaj	False
locations[1].source.display_name	arXiv (Cornell University)
locations[1].source.host_organization	https://openalex.org/I205783295
locations[1].source.host_organization_name	Cornell University
locations[1].source.host_organization_lineage	https://openalex.org/I205783295
locations[1].license
locations[1].pdf_url
locations[1].version
locations[1].raw_type	article
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published
locations[1].raw_source_name
locations[1].landing_page_url	https://doi.org/10.48550/arxiv.2505.05992
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5101675965
authorships[0].author.orcid	https://orcid.org/0009-0001-6620-4343
authorships[0].author.display_name	Yongsheng Huang
authorships[0].author_position	first
authorships[0].raw_author_name	Huang, Yongsheng
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5010309828
authorships[1].author.orcid	https://orcid.org/0000-0002-0686-8404
authorships[1].author.display_name	Peibo Duan
authorships[1].author_position	middle
authorships[1].raw_author_name	Duan, Peibo
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5100408904
authorships[2].author.orcid	https://orcid.org/0000-0002-1425-1738
authorships[2].author.display_name	Kai Sun
authorships[2].author_position	middle
authorships[2].raw_author_name	Sun, Kai
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5100687487
authorships[3].author.orcid	https://orcid.org/0000-0003-2349-3138
authorships[3].author.display_name	Changsheng Zhang
authorships[3].author_position	middle
authorships[3].raw_author_name	Zhang, Changsheng
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5100392843
authorships[4].author.orcid	https://orcid.org/0000-0002-4879-0211
authorships[4].author.display_name	Bin Zhang
authorships[4].author_position	last
authorships[4].raw_author_name	Zhang, Bin
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5030409594
authorships[5].author.orcid	https://orcid.org/0000-0003-4329-8735
authorships[5].author.display_name	Mingkun Xu
authorships[5].author_position	middle
authorships[5].raw_author_name	Xu, Mingkun
authorships[5].is_corresponding	False
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://arxiv.org/pdf/2505.05992
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	CogniSNN: A First Exploration to Random Graph Architecture based Spiking Neural Networks with Enhanced Expandability and Neuroplasticity
has_fulltext	False
is_retracted	False
updated_date	2025-12-07T09:55:28.804818
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2505.05992
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S4306400194
best_oa_location.source.issn
best_oa_location.source.type	repository
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l
best_oa_location.source.is_core	False
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	arXiv (Cornell University)
best_oa_location.source.host_organization	https://openalex.org/I205783295
best_oa_location.source.host_organization_name	Cornell University
best_oa_location.source.host_organization_lineage	https://openalex.org/I205783295
best_oa_location.license
best_oa_location.pdf_url	https://arxiv.org/pdf/2505.05992
best_oa_location.version	submittedVersion
best_oa_location.raw_type	text
best_oa_location.license_id
best_oa_location.is_accepted	False
best_oa_location.is_published	False
best_oa_location.raw_source_name
best_oa_location.landing_page_url	http://arxiv.org/abs/2505.05992
primary_location.id	pmh:oai:arXiv.org:2505.05992
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S4306400194
primary_location.source.issn
primary_location.source.type	repository
primary_location.source.is_oa	True
primary_location.source.issn_l
primary_location.source.is_core	False
primary_location.source.is_in_doaj	False
primary_location.source.display_name	arXiv (Cornell University)
primary_location.source.host_organization	https://openalex.org/I205783295
primary_location.source.host_organization_name	Cornell University
primary_location.source.host_organization_lineage	https://openalex.org/I205783295
primary_location.license
primary_location.pdf_url	https://arxiv.org/pdf/2505.05992
primary_location.version	submittedVersion
primary_location.raw_type	text
primary_location.license_id
primary_location.is_accepted	False
primary_location.is_published	False
primary_location.raw_source_name
primary_location.landing_page_url	http://arxiv.org/abs/2505.05992
publication_date	2025-05-09
publication_year	2025
referenced_works_count	0
abstract_inverted_index.5	130
abstract_inverted_index.a	34, 60, 78, 169
abstract_inverted_index.3%	137
abstract_inverted_index.5%	139
abstract_inverted_index.as	75, 77
abstract_inverted_index.by	58
abstract_inverted_index.in	2, 7, 71, 102, 115, 124, 145
abstract_inverted_index.of	56, 95, 164
abstract_inverted_index.on	89, 177
abstract_inverted_index.or	153
abstract_inverted_index.to	15, 24, 67, 85, 138, 152
abstract_inverted_index.we	50
abstract_inverted_index.RGA	100
abstract_inverted_index.SNN	39, 47, 166
abstract_inverted_index.The	132
abstract_inverted_index.and	54, 98, 167
abstract_inverted_index.are	150
abstract_inverted_index.for	38, 172
abstract_inverted_index.new	35, 90, 147, 170
abstract_inverted_index.old	104, 157
abstract_inverted_index.the	52, 93, 96, 99, 103, 125, 156, 162
abstract_inverted_index.This	31, 159
abstract_inverted_index.data	97
abstract_inverted_index.from	155
abstract_inverted_index.node	65
abstract_inverted_index.only	129
abstract_inverted_index.path	171
abstract_inverted_index.show	107
abstract_inverted_index.that	82, 108, 149
abstract_inverted_index.well	76
abstract_inverted_index.with	40, 110, 118, 128
abstract_inverted_index.95.5%	122
abstract_inverted_index.based	176
abstract_inverted_index.fewer	119
abstract_inverted_index.graph	42, 73, 178
abstract_inverted_index.mimic	25
abstract_inverted_index.ones.	158
abstract_inverted_index.paper	32
abstract_inverted_index.paves	168
abstract_inverted_index.study	160
abstract_inverted_index.task.	105
abstract_inverted_index.tasks	91, 148
abstract_inverted_index.their	10, 22
abstract_inverted_index.while	141
abstract_inverted_index.(RGA),	44
abstract_inverted_index.(SNNs)	6
abstract_inverted_index.deeper	72
abstract_inverted_index.highly	13
abstract_inverted_index.neural	4, 18, 64
abstract_inverted_index.random	41
abstract_inverted_index.remain	12
abstract_inverted_index.tasks,	9
abstract_inverted_index.termed	45
abstract_inverted_index.(ANNs),	20
abstract_inverted_index.Despite	0
abstract_inverted_index.ResNode	112
abstract_inverted_index.ability	23
abstract_inverted_index.between	28
abstract_inverted_index.dataset	127
abstract_inverted_index.enables	83
abstract_inverted_index.improve	51
abstract_inverted_index.learned	101
abstract_inverted_index.natural	26
abstract_inverted_index.network	69
abstract_inverted_index.perform	86
abstract_inverted_index.similar	14, 151
abstract_inverted_index.spiking	3, 62
abstract_inverted_index.theory.	179
abstract_inverted_index.CogniSNN	57, 84, 109
abstract_inverted_index.advances	1
abstract_inverted_index.approach	135
abstract_inverted_index.critical	79, 133
abstract_inverted_index.datasets	117
abstract_inverted_index.develops	33
abstract_inverted_index.distinct	154
abstract_inverted_index.expected	143
abstract_inverted_index.features	94
abstract_inverted_index.inspired	174
abstract_inverted_index.learning	88, 146
abstract_inverted_index.modeling	36
abstract_inverted_index.modified	61
abstract_inverted_index.networks	5, 19, 175
abstract_inverted_index.neurons.	30
abstract_inverted_index.numerous	8
abstract_inverted_index.paradigm	37
abstract_inverted_index.performs	113
abstract_inverted_index.residual	63
abstract_inverted_index.(ResNode)	66
abstract_inverted_index.RGA-based	165
abstract_inverted_index.achieving	121
abstract_inverted_index.algorithm	81
abstract_inverted_index.continual	87
abstract_inverted_index.decreases	136
abstract_inverted_index.pathways,	74
abstract_inverted_index.potential	163
abstract_inverted_index.precision	123
abstract_inverted_index.showcases	161
abstract_inverted_index.artificial	17
abstract_inverted_index.biological	29
abstract_inverted_index.counteract	68
abstract_inverted_index.forgetting	140
abstract_inverted_index.leveraging	92
abstract_inverted_index.path-based	80, 134
abstract_inverted_index.timesteps.	131
abstract_inverted_index.(CogniSNN).	48
abstract_inverted_index.DVS-Gesture	126
abstract_inverted_index.Experiments	106
abstract_inverted_index.connections	27
abstract_inverted_index.degradation	70
abstract_inverted_index.introducing	59
abstract_inverted_index.maintaining	142
abstract_inverted_index.parameters,	120
abstract_inverted_index.performance	144
abstract_inverted_index.re-designed	111
abstract_inverted_index.restricting	21
abstract_inverted_index.traditional	16
abstract_inverted_index.Furthermore,	49
abstract_inverted_index.architecture	43
abstract_inverted_index.biologically	173
abstract_inverted_index.neuromorphic	116
abstract_inverted_index.architectures	11
abstract_inverted_index.expandability	53
abstract_inverted_index.outstandingly	114
abstract_inverted_index.Cognition-aware	46
abstract_inverted_index.neuroplasticity	55
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	6
citation_normalized_percentile