Diffusion Learning with Partial Agent Participation and Local Updates Article Swipe

PDF

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2505.11307

Diffusion learning is a framework that endows edge devices with advanced intelligence. By processing and analyzing data locally and allowing each agent to communicate with its immediate neighbors, diffusion effectively protects the privacy of edge devices, enables real-time response, and reduces reliance on central servers. However, traditional diffusion learning relies on communication at every iteration, leading to communication overhead, especially with large learning models. Furthermore, the inherent volatility of edge devices, stemming from power outages or signal loss, poses challenges to reliable communication between neighboring agents. To mitigate these issues, this paper investigates an enhanced diffusion learning approach incorporating local updates and partial agent participation. Local updates will curtail communication frequency, while partial agent participation will allow for the inclusion of agents based on their availability. We prove that the resulting algorithm is stable in the mean-square error sense and provide a tight analysis of its Mean-Square-Deviation (MSD) performance. Various numerical experiments are conducted to illustrate our theoretical findings.

Related Topics

List Of Footballers With 500 Or More Goals

Fire With Fire (2012 Film)

It Ends With Us (Film)

My Life With The Walter Boys

Bestiality With A Donkey

Destined With You

The Man With The Iron Fists

Man With A Movie Camera

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2505.11307
PDF: https://arxiv.org/pdf/2505.11307
OA Status: green
OpenAlex ID: https://openalex.org/W4417094053

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4417094053

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2505.11307

Digital Object Identifier
Title: Diffusion Learning with Partial Agent Participation and Local Updates

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-05-16

Full publication date if available
Authors: Elsa Rizk, Kun Yuan, Ali H. Sayed

List of authors in order
Landing page: https://arxiv.org/abs/2505.11307

Publisher landing page
PDF URL: https://arxiv.org/pdf/2505.11307

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/2505.11307

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4417094053
doi	https://doi.org/10.48550/arxiv.2505.11307
ids.doi	https://doi.org/10.48550/arxiv.2505.11307
ids.openalex	https://openalex.org/W4417094053
fwci
type	preprint
title	Diffusion Learning with Partial Agent Participation and Local Updates
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:2505.11307
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/2505.11307
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/2505.11307
locations[1].id	doi:10.48550/arxiv.2505.11307
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.2505.11307
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5040354724
authorships[0].author.orcid	https://orcid.org/0000-0001-6902-2329
authorships[0].author.display_name	Elsa Rizk
authorships[0].author_position	first
authorships[0].raw_author_name	Rizk, Elsa
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5100614598
authorships[1].author.orcid	https://orcid.org/0000-0001-8394-8187
authorships[1].author.display_name	Kun Yuan
authorships[1].author_position	middle
authorships[1].raw_author_name	Yuan, Kun
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5091103447
authorships[2].author.orcid	https://orcid.org/0000-0002-5125-5519
authorships[2].author.display_name	Ali H. Sayed
authorships[2].author_position	last
authorships[2].raw_author_name	Sayed, Ali H.
authorships[2].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/2505.11307
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Diffusion Learning with Partial Agent Participation and Local Updates
has_fulltext	False
is_retracted	False
updated_date	2025-12-07T16:30:24.675874
primary_topic
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2505.11307
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/2505.11307
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/2505.11307
primary_location.id	pmh:oai:arXiv.org:2505.11307
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/2505.11307
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/2505.11307
publication_date	2025-05-16
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	3, 141
abstract_inverted_index.By	12
abstract_inverted_index.To	86
abstract_inverted_index.We	126
abstract_inverted_index.an	93
abstract_inverted_index.at	52
abstract_inverted_index.in	134
abstract_inverted_index.is	2, 132
abstract_inverted_index.of	33, 68, 120, 144
abstract_inverted_index.on	42, 50, 123
abstract_inverted_index.or	75
abstract_inverted_index.to	22, 56, 80, 154
abstract_inverted_index.and	14, 18, 39, 101, 139
abstract_inverted_index.are	152
abstract_inverted_index.for	117
abstract_inverted_index.its	25, 145
abstract_inverted_index.our	156
abstract_inverted_index.the	31, 65, 118, 129, 135
abstract_inverted_index.data	16
abstract_inverted_index.each	20
abstract_inverted_index.edge	7, 34, 69
abstract_inverted_index.from	72
abstract_inverted_index.that	5, 128
abstract_inverted_index.this	90
abstract_inverted_index.will	107, 115
abstract_inverted_index.with	9, 24, 60
abstract_inverted_index.(MSD)	147
abstract_inverted_index.Local	105
abstract_inverted_index.agent	21, 103, 113
abstract_inverted_index.allow	116
abstract_inverted_index.based	122
abstract_inverted_index.error	137
abstract_inverted_index.every	53
abstract_inverted_index.large	61
abstract_inverted_index.local	99
abstract_inverted_index.loss,	77
abstract_inverted_index.paper	91
abstract_inverted_index.poses	78
abstract_inverted_index.power	73
abstract_inverted_index.prove	127
abstract_inverted_index.sense	138
abstract_inverted_index.their	124
abstract_inverted_index.these	88
abstract_inverted_index.tight	142
abstract_inverted_index.while	111
abstract_inverted_index.agents	121
abstract_inverted_index.endows	6
abstract_inverted_index.relies	49
abstract_inverted_index.signal	76
abstract_inverted_index.stable	133
abstract_inverted_index.Various	149
abstract_inverted_index.agents.	85
abstract_inverted_index.between	83
abstract_inverted_index.central	43
abstract_inverted_index.curtail	108
abstract_inverted_index.devices	8
abstract_inverted_index.enables	36
abstract_inverted_index.issues,	89
abstract_inverted_index.leading	55
abstract_inverted_index.locally	17
abstract_inverted_index.models.	63
abstract_inverted_index.outages	74
abstract_inverted_index.partial	102, 112
abstract_inverted_index.privacy	32
abstract_inverted_index.provide	140
abstract_inverted_index.reduces	40
abstract_inverted_index.updates	100, 106
abstract_inverted_index.However,	45
abstract_inverted_index.advanced	10
abstract_inverted_index.allowing	19
abstract_inverted_index.analysis	143
abstract_inverted_index.approach	97
abstract_inverted_index.devices,	35, 70
abstract_inverted_index.enhanced	94
abstract_inverted_index.inherent	66
abstract_inverted_index.learning	1, 48, 62, 96
abstract_inverted_index.mitigate	87
abstract_inverted_index.protects	30
abstract_inverted_index.reliable	81
abstract_inverted_index.reliance	41
abstract_inverted_index.servers.	44
abstract_inverted_index.stemming	71
abstract_inverted_index.Diffusion	0
abstract_inverted_index.algorithm	131
abstract_inverted_index.analyzing	15
abstract_inverted_index.conducted	153
abstract_inverted_index.diffusion	28, 47, 95
abstract_inverted_index.findings.	158
abstract_inverted_index.framework	4
abstract_inverted_index.immediate	26
abstract_inverted_index.inclusion	119
abstract_inverted_index.numerical	150
abstract_inverted_index.overhead,	58
abstract_inverted_index.real-time	37
abstract_inverted_index.response,	38
abstract_inverted_index.resulting	130
abstract_inverted_index.challenges	79
abstract_inverted_index.especially	59
abstract_inverted_index.frequency,	110
abstract_inverted_index.illustrate	155
abstract_inverted_index.iteration,	54
abstract_inverted_index.neighbors,	27
abstract_inverted_index.processing	13
abstract_inverted_index.volatility	67
abstract_inverted_index.communicate	23
abstract_inverted_index.effectively	29
abstract_inverted_index.experiments	151
abstract_inverted_index.mean-square	136
abstract_inverted_index.neighboring	84
abstract_inverted_index.theoretical	157
abstract_inverted_index.traditional	46
abstract_inverted_index.Furthermore,	64
abstract_inverted_index.investigates	92
abstract_inverted_index.performance.	148
abstract_inverted_index.availability.	125
abstract_inverted_index.communication	51, 57, 82, 109
abstract_inverted_index.incorporating	98
abstract_inverted_index.intelligence.	11
abstract_inverted_index.participation	114
abstract_inverted_index.participation.	104
abstract_inverted_index.Mean-Square-Deviation	146
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	3
citation_normalized_percentile