Structure-prior Informed Diffusion Model for Graph Source Localization with Limited Data Article Swipe

View

Hongyi Chen , Jingtao Ding , Xiaojun Liang , Yongbo Li , Xiao–Ping Zhang ·

YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.1145/3746252.3761146

Source localization in graph information propagation is essential for mitigating network disruptions, including misinformation spread, cyber threats, and infrastructure failures. Existing deep generative approaches face significant challenges in real-world applications due to limited propagation data availability. We present SIDSL (\textbf{S}tructure-prior \textbf{I}nformed \textbf{D}iffusion model for \textbf{S}ource \textbf{L}ocalization), a generative diffusion framework that leverages topology-aware priors to enable robust source localization with limited data. SIDSL addresses three key challenges: unknown propagation patterns through structure-based source estimations via graph label propagation, complex topology-propagation relationships via a propagation-enhanced conditional denoiser with GNN-parameterized label propagation module, and class imbalance through structure-prior biased diffusion initialization. By learning pattern-invariant features from synthetic data generated by established propagation models, SIDSL enables effective knowledge transfer to real-world scenarios. Experimental evaluation on four real-world datasets demonstrates superior performance with 7.5-13.3\% F1 score improvements over baselines, including over 19\% improvement in few-shot and 40\% in zero-shot settings, validating the framework's effectiveness for practical source localization. Our code can be found \href{https://github.com/tsinghua-fib-lab/SIDSL}{here}.

Related Topics

Concepts

No concepts available.

Metadata

Type: preprint
Language: en
Landing Page: https://doi.org/10.1145/3746252.3761146
OA Status: gold
OpenAlex ID: https://openalex.org/W4415251290

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4415251290

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.1145/3746252.3761146

Digital Object Identifier
Title: Structure-prior Informed Diffusion Model for Graph Source Localization with Limited Data

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2025

Year of publication
Publication date: 2025-11-08

Full publication date if available
Authors: Hongyi Chen, Jingtao Ding, Xiaojun Liang, Yongbo Li, Xiao–Ping Zhang

List of authors in order
Landing page: https://doi.org/10.1145/3746252.3761146

Publisher landing page
Open access: Yes

Whether a free full text is available
OA status: gold

Open access status per OpenAlex
OA URL: https://doi.org/10.1145/3746252.3761146

Direct OA link when available
Cited by: 0

Total citation count in OpenAlex

Full payload

id	https://openalex.org/W4415251290
doi	https://doi.org/10.1145/3746252.3761146
ids.doi	https://doi.org/10.1145/3746252.3761146
ids.openalex	https://openalex.org/W4415251290
fwci	0.0
type	preprint
title	Structure-prior Informed Diffusion Model for Graph Source Localization with Limited Data
biblio.issue
biblio.volume
biblio.last_page	259
biblio.first_page	250
topics[0].id	https://openalex.org/T11273
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.957099974155426
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1702
topics[0].subfield.display_name	Artificial Intelligence
topics[0].display_name	Advanced Graph Neural Networks
topics[1].id	https://openalex.org/T11307
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9311000108718872
topics[1].domain.id	https://openalex.org/domains/3
topics[1].domain.display_name	Physical Sciences
topics[1].subfield.id	https://openalex.org/subfields/1702
topics[1].subfield.display_name	Artificial Intelligence
topics[1].display_name	Domain Adaptation and Few-Shot Learning
is_xpac	False
apc_list
apc_paid
language	en
locations[0].id	doi:10.1145/3746252.3761146
locations[0].is_oa	True
locations[0].source
locations[0].license	cc-by-nc-sa
locations[0].pdf_url
locations[0].version	publishedVersion
locations[0].raw_type	proceedings-article
locations[0].license_id	https://openalex.org/licenses/cc-by-nc-sa
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	Proceedings of the 34th ACM International Conference on Information and Knowledge Management
locations[0].landing_page_url	https://doi.org/10.1145/3746252.3761146
locations[1].id	pmh:oai:arXiv.org:2502.17928
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	https://arxiv.org/pdf/2502.17928
locations[1].version	submittedVersion
locations[1].raw_type	text
locations[1].license_id
locations[1].is_accepted	False
locations[1].is_published	False
locations[1].raw_source_name
locations[1].landing_page_url	http://arxiv.org/abs/2502.17928
indexed_in	arxiv, crossref
authorships[0].author.id	https://openalex.org/A5100428551
authorships[0].author.orcid	https://orcid.org/0009-0008-0777-3942
authorships[0].author.display_name	Hongyi Chen
authorships[0].countries	CN
authorships[0].affiliations[0].institution_ids	https://openalex.org/I99065089
authorships[0].affiliations[0].raw_affiliation_string	Shenzhen Key Laboratory of Ubiquitous Data Enabling, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China
authorships[0].institutions[0].id	https://openalex.org/I99065089
authorships[0].institutions[0].ror	https://ror.org/03cve4549
authorships[0].institutions[0].type	education
authorships[0].institutions[0].lineage	https://openalex.org/I99065089
authorships[0].institutions[0].country_code	CN
authorships[0].institutions[0].display_name	Tsinghua University
authorships[0].author_position	first
authorships[0].raw_author_name	Hongyi Chen
authorships[0].is_corresponding	False
authorships[0].raw_affiliation_strings	Shenzhen Key Laboratory of Ubiquitous Data Enabling, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China and Pengcheng Laboratory, Shenzhen, China
authorships[1].author.id	https://openalex.org/A5101809174
authorships[1].author.orcid	https://orcid.org/0000-0003-1487-3470
authorships[1].author.display_name	Jingtao Ding
authorships[1].countries	CN
authorships[1].affiliations[0].institution_ids	https://openalex.org/I99065089
authorships[1].affiliations[0].raw_affiliation_string	Department of Electronic Engineering, Tsinghua University, Beijing, China
authorships[1].institutions[0].id	https://openalex.org/I99065089
authorships[1].institutions[0].ror	https://ror.org/03cve4549
authorships[1].institutions[0].type	education
authorships[1].institutions[0].lineage	https://openalex.org/I99065089
authorships[1].institutions[0].country_code	CN
authorships[1].institutions[0].display_name	Tsinghua University
authorships[1].author_position	middle
authorships[1].raw_author_name	Jingtao Ding
authorships[1].is_corresponding	False
authorships[1].raw_affiliation_strings	Department of Electronic Engineering, Tsinghua University, Beijing, China
authorships[2].author.id	https://openalex.org/A5030000317
authorships[2].author.orcid	https://orcid.org/0000-0003-1712-7983
authorships[2].author.display_name	Xiaojun Liang
authorships[2].countries	CN
authorships[2].affiliations[0].institution_ids	https://openalex.org/I4210136793
authorships[2].affiliations[0].raw_affiliation_string	Pengcheng Laboratory, Shenzhen, China
authorships[2].institutions[0].id	https://openalex.org/I4210136793
authorships[2].institutions[0].ror	https://ror.org/03qdqbt06
authorships[2].institutions[0].type	facility
authorships[2].institutions[0].lineage	https://openalex.org/I4210136793
authorships[2].institutions[0].country_code	CN
authorships[2].institutions[0].display_name	Peng Cheng Laboratory
authorships[2].author_position	middle
authorships[2].raw_author_name	Xiaojun Liang
authorships[2].is_corresponding	False
authorships[2].raw_affiliation_strings	Pengcheng Laboratory, Shenzhen, China
authorships[3].author.id	https://openalex.org/A5100665121
authorships[3].author.orcid	https://orcid.org/0000-0003-2699-9951
authorships[3].author.display_name	Yongbo Li
authorships[3].countries	CN
authorships[3].affiliations[0].institution_ids	https://openalex.org/I99065089
authorships[3].affiliations[0].raw_affiliation_string	Department of Electronic Engineering, Tsinghua University, Beijing, China
authorships[3].institutions[0].id	https://openalex.org/I99065089
authorships[3].institutions[0].ror	https://ror.org/03cve4549
authorships[3].institutions[0].type	education
authorships[3].institutions[0].lineage	https://openalex.org/I99065089
authorships[3].institutions[0].country_code	CN
authorships[3].institutions[0].display_name	Tsinghua University
authorships[3].author_position	middle
authorships[3].raw_author_name	Yong Li
authorships[3].is_corresponding	False
authorships[3].raw_affiliation_strings	Department of Electronic Engineering, Tsinghua University, Beijing, China
authorships[4].author.id	https://openalex.org/A5100363146
authorships[4].author.orcid	https://orcid.org/0000-0001-5241-0069
authorships[4].author.display_name	Xiao–Ping Zhang
authorships[4].countries	CN
authorships[4].affiliations[0].institution_ids	https://openalex.org/I3131625388, https://openalex.org/I99065089
authorships[4].affiliations[0].raw_affiliation_string	Shenzhen Key Laboratory of Ubiquitous Data Enabling, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
authorships[4].institutions[0].id	https://openalex.org/I99065089
authorships[4].institutions[0].ror	https://ror.org/03cve4549
authorships[4].institutions[0].type	education
authorships[4].institutions[0].lineage	https://openalex.org/I99065089
authorships[4].institutions[0].country_code	CN
authorships[4].institutions[0].display_name	Tsinghua University
authorships[4].institutions[1].id	https://openalex.org/I3131625388
authorships[4].institutions[1].ror	https://ror.org/05f5j6225
authorships[4].institutions[1].type	education
authorships[4].institutions[1].lineage	https://openalex.org/I3131625388
authorships[4].institutions[1].country_code	CN
authorships[4].institutions[1].display_name	University Town of Shenzhen
authorships[4].author_position	last
authorships[4].raw_author_name	Zhang, Xiao-Ping
authorships[4].is_corresponding	False
authorships[4].raw_affiliation_strings	Shenzhen Key Laboratory of Ubiquitous Data Enabling, Shenzhen International Graduate School, Tsinghua University, Shenzhen, China
has_content.pdf	False
has_content.grobid_xml	False
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://doi.org/10.1145/3746252.3761146
open_access.oa_status	gold
open_access.any_repository_has_fulltext	False
created_date	2025-10-16T00:00:00
display_name	Structure-prior Informed Diffusion Model for Graph Source Localization with Limited Data
has_fulltext	False
is_retracted	False
updated_date	2025-11-09T23:09:16.995542
primary_topic.id	https://openalex.org/T11273
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.957099974155426
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1702
primary_topic.subfield.display_name	Artificial Intelligence
primary_topic.display_name	Advanced Graph Neural Networks
cited_by_count	0
locations_count	2
best_oa_location.id	doi:10.1145/3746252.3761146
best_oa_location.is_oa	True
best_oa_location.source
best_oa_location.license	cc-by-nc-sa
best_oa_location.pdf_url
best_oa_location.version	publishedVersion
best_oa_location.raw_type	proceedings-article
best_oa_location.license_id	https://openalex.org/licenses/cc-by-nc-sa
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	Proceedings of the 34th ACM International Conference on Information and Knowledge Management
best_oa_location.landing_page_url	https://doi.org/10.1145/3746252.3761146
primary_location.id	doi:10.1145/3746252.3761146
primary_location.is_oa	True
primary_location.source
primary_location.license	cc-by-nc-sa
primary_location.pdf_url
primary_location.version	publishedVersion
primary_location.raw_type	proceedings-article
primary_location.license_id	https://openalex.org/licenses/cc-by-nc-sa
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	Proceedings of the 34th ACM International Conference on Information and Knowledge Management
primary_location.landing_page_url	https://doi.org/10.1145/3746252.3761146
publication_date	2025-11-08
publication_year	2025
referenced_works_count	0
abstract_inverted_index.a	46, 82
abstract_inverted_index.By	99
abstract_inverted_index.F1	130
abstract_inverted_index.We	36
abstract_inverted_index.be	157
abstract_inverted_index.by	107
abstract_inverted_index.in	2, 27, 139, 143
abstract_inverted_index.is	6
abstract_inverted_index.on	121
abstract_inverted_index.to	31, 54, 116
abstract_inverted_index.Our	154
abstract_inverted_index.and	17, 91, 141
abstract_inverted_index.can	156
abstract_inverted_index.due	30
abstract_inverted_index.for	8, 43, 150
abstract_inverted_index.key	65
abstract_inverted_index.the	147
abstract_inverted_index.via	74, 81
abstract_inverted_index.19\%	137
abstract_inverted_index.40\%	142
abstract_inverted_index.code	155
abstract_inverted_index.data	34, 105
abstract_inverted_index.deep	21
abstract_inverted_index.face	24
abstract_inverted_index.four	122
abstract_inverted_index.from	103
abstract_inverted_index.over	133, 136
abstract_inverted_index.that	50
abstract_inverted_index.with	59, 86, 128
abstract_inverted_index.SIDSL	38, 62, 111
abstract_inverted_index.class	92
abstract_inverted_index.cyber	15
abstract_inverted_index.data.	61
abstract_inverted_index.found	158
abstract_inverted_index.graph	3, 75
abstract_inverted_index.label	76, 88
abstract_inverted_index.model	42
abstract_inverted_index.score	131
abstract_inverted_index.three	64
abstract_inverted_index.Source	0
abstract_inverted_index.biased	96
abstract_inverted_index.enable	55
abstract_inverted_index.priors	53
abstract_inverted_index.robust	56
abstract_inverted_index.source	57, 72, 152
abstract_inverted_index.complex	78
abstract_inverted_index.enables	112
abstract_inverted_index.limited	32, 60
abstract_inverted_index.models,	110
abstract_inverted_index.module,	90
abstract_inverted_index.network	10
abstract_inverted_index.present	37
abstract_inverted_index.spread,	14
abstract_inverted_index.through	70, 94
abstract_inverted_index.unknown	67
abstract_inverted_index.Existing	20
abstract_inverted_index.datasets	124
abstract_inverted_index.denoiser	85
abstract_inverted_index.features	102
abstract_inverted_index.few-shot	140
abstract_inverted_index.learning	100
abstract_inverted_index.patterns	69
abstract_inverted_index.superior	126
abstract_inverted_index.threats,	16
abstract_inverted_index.transfer	115
abstract_inverted_index.addresses	63
abstract_inverted_index.diffusion	48, 97
abstract_inverted_index.effective	113
abstract_inverted_index.essential	7
abstract_inverted_index.failures.	19
abstract_inverted_index.framework	49
abstract_inverted_index.generated	106
abstract_inverted_index.imbalance	93
abstract_inverted_index.including	12, 135
abstract_inverted_index.knowledge	114
abstract_inverted_index.leverages	51
abstract_inverted_index.practical	151
abstract_inverted_index.settings,	145
abstract_inverted_index.synthetic	104
abstract_inverted_index.zero-shot	144
abstract_inverted_index.7.5-13.3\%	129
abstract_inverted_index.approaches	23
abstract_inverted_index.baselines,	134
abstract_inverted_index.challenges	26
abstract_inverted_index.evaluation	120
abstract_inverted_index.generative	22, 47
abstract_inverted_index.mitigating	9
abstract_inverted_index.real-world	28, 117, 123
abstract_inverted_index.scenarios.	118
abstract_inverted_index.validating	146
abstract_inverted_index.challenges:	66
abstract_inverted_index.conditional	84
abstract_inverted_index.established	108
abstract_inverted_index.estimations	73
abstract_inverted_index.framework's	148
abstract_inverted_index.improvement	138
abstract_inverted_index.information	4
abstract_inverted_index.performance	127
abstract_inverted_index.propagation	5, 33, 68, 89, 109
abstract_inverted_index.significant	25
abstract_inverted_index.Experimental	119
abstract_inverted_index.applications	29
abstract_inverted_index.demonstrates	125
abstract_inverted_index.disruptions,	11
abstract_inverted_index.improvements	132
abstract_inverted_index.localization	1, 58
abstract_inverted_index.propagation,	77
abstract_inverted_index.availability.	35
abstract_inverted_index.effectiveness	149
abstract_inverted_index.localization.	153
abstract_inverted_index.relationships	80
abstract_inverted_index.infrastructure	18
abstract_inverted_index.misinformation	13
abstract_inverted_index.topology-aware	52
abstract_inverted_index.\textbf{S}ource	44
abstract_inverted_index.initialization.	98
abstract_inverted_index.structure-based	71
abstract_inverted_index.structure-prior	95
abstract_inverted_index.GNN-parameterized	87
abstract_inverted_index.\textbf{I}nformed	40
abstract_inverted_index.pattern-invariant	101
abstract_inverted_index.\textbf{D}iffusion	41
abstract_inverted_index.propagation-enhanced	83
abstract_inverted_index.topology-propagation	79
abstract_inverted_index.\textbf{L}ocalization),	45
abstract_inverted_index.(\textbf{S}tructure-prior	39
abstract_inverted_index.\href{https://github.com/tsinghua-fib-lab/SIDSL}{here}.	159
cited_by_percentile_year
countries_distinct_count	1
institutions_distinct_count	5
citation_normalized_percentile.value	0.22380901
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	True