DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile Networks Article Swipe
Q. Li
,
Jiansheng Li
,
S Chai
,
Y. Thomas Hou
,
Xiaowei Shao
,
Fangfang Li
,
Kaifeng Han
,
Guangxu Zhu
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2511.11737
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2511.11737
Diagnosing the root causes of Quality of Experience (QoE) degradations in operational mobile networks is challenging due to complex cross-layer interactions among kernel performance indicators (KPIs) and the scarcity of reliable expert annotations. Although rule-based heuristics can generate labels at scale, they are noisy and coarse-grained, limiting the accuracy of purely data-driven approaches. To address this, we propose DK-Root, a joint data-and-knowledge-driven framework that unifies scalable weak supervision with precise expert guidance for robust root-cause analysis. DK-Root first pretrains an encoder via contrastive representation learning using abundant rule-based labels while explicitly denoising their noise through a supervised contrastive objective. To supply task-faithful data augmentation, we introduce a class-conditional diffusion model that generates KPIs sequences preserving root-cause semantics, and by controlling reverse diffusion steps, it produces weak and strong augmentations that improve intra-class compactness and inter-class separability. Finally, the encoder and the lightweight classifier are jointly fine-tuned with scarce expert-verified labels to sharpen decision boundaries. Extensive experiments on a real-world, operator-grade dataset demonstrate state-of-the-art accuracy, with DK-Root surpassing traditional ML and recent semi-supervised time-series methods. Ablations confirm the necessity of the conditional diffusion augmentation and the pretrain-finetune design, validating both representation quality and classification gains.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/2511.11737
- https://arxiv.org/pdf/2511.11737
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4416350498
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416350498Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2511.11737Digital Object Identifier
- Title
-
DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile NetworksWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2025Year of publication
- Publication date
-
2025-11-13Full publication date if available
- Authors
-
Q. Li, Jiansheng Li, S Chai, Y. Thomas Hou, Xiaowei Shao, Fangfang Li, Kaifeng Han, Guangxu ZhuList of authors in order
- Landing page
-
https://arxiv.org/abs/2511.11737Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2511.11737Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2511.11737Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416350498 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2511.11737 |
| ids.doi | https://doi.org/10.48550/arxiv.2511.11737 |
| ids.openalex | https://openalex.org/W4416350498 |
| fwci | |
| type | preprint |
| title | DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | |
| locations[0].id | pmh:oai:arXiv.org:2511.11737 |
| 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/2511.11737 |
| 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/2511.11737 |
| locations[1].id | doi:10.48550/arxiv.2511.11737 |
| 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.2511.11737 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5101913497 |
| authorships[0].author.orcid | https://orcid.org/0009-0002-8803-352X |
| authorships[0].author.display_name | Q. Li |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Li, Qizhe |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5100631199 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3708-3677 |
| authorships[1].author.display_name | Jiansheng Li |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Li, Jiansheng |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5015000664 |
| authorships[2].author.orcid | https://orcid.org/0009-0003-7297-2351 |
| authorships[2].author.display_name | S Chai |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Chai, Shuqi |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5059824798 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-3716-5768 |
| authorships[3].author.display_name | Y. Thomas Hou |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Hou, Yuzhou |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5050975050 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-2603-057X |
| authorships[4].author.display_name | Xiaowei Shao |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Shao, Xinhua |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100404522 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-7392-586X |
| authorships[5].author.display_name | Fangfang Li |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Li, Fangfang |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5043358532 |
| authorships[6].author.orcid | https://orcid.org/0000-0001-6940-073X |
| authorships[6].author.display_name | Kaifeng Han |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Han, Kaifeng |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5004583148 |
| authorships[7].author.orcid | https://orcid.org/0000-0001-9532-9201 |
| authorships[7].author.display_name | Guangxu Zhu |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Zhu, Guangxu |
| authorships[7].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/2511.11737 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-11-19T00:00:00 |
| display_name | DK-Root: A Joint Data-and-Knowledge-Driven Framework for Root Cause Analysis of QoE Degradations in Mobile Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-28T11:54:44.792462 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2511.11737 |
| 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/2511.11737 |
| 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/2511.11737 |
| primary_location.id | pmh:oai:arXiv.org:2511.11737 |
| 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/2511.11737 |
| 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/2511.11737 |
| publication_date | 2025-11-13 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 59, 95, 106, 157 |
| abstract_inverted_index.ML | 168 |
| abstract_inverted_index.To | 53, 99 |
| abstract_inverted_index.an | 79 |
| abstract_inverted_index.at | 39 |
| abstract_inverted_index.by | 118 |
| abstract_inverted_index.in | 10 |
| abstract_inverted_index.is | 14 |
| abstract_inverted_index.it | 123 |
| abstract_inverted_index.of | 4, 6, 29, 49, 178 |
| abstract_inverted_index.on | 156 |
| abstract_inverted_index.to | 17, 150 |
| abstract_inverted_index.we | 56, 104 |
| abstract_inverted_index.and | 26, 44, 117, 126, 133, 139, 169, 183, 191 |
| abstract_inverted_index.are | 42, 143 |
| abstract_inverted_index.can | 36 |
| abstract_inverted_index.due | 16 |
| abstract_inverted_index.for | 72 |
| abstract_inverted_index.the | 1, 27, 47, 137, 140, 176, 179, 184 |
| abstract_inverted_index.via | 81 |
| abstract_inverted_index.KPIs | 112 |
| abstract_inverted_index.both | 188 |
| abstract_inverted_index.data | 102 |
| abstract_inverted_index.root | 2 |
| abstract_inverted_index.that | 63, 110, 129 |
| abstract_inverted_index.they | 41 |
| abstract_inverted_index.weak | 66, 125 |
| abstract_inverted_index.with | 68, 146, 164 |
| abstract_inverted_index.(QoE) | 8 |
| abstract_inverted_index.among | 21 |
| abstract_inverted_index.first | 77 |
| abstract_inverted_index.joint | 60 |
| abstract_inverted_index.model | 109 |
| abstract_inverted_index.noise | 93 |
| abstract_inverted_index.noisy | 43 |
| abstract_inverted_index.their | 92 |
| abstract_inverted_index.this, | 55 |
| abstract_inverted_index.using | 85 |
| abstract_inverted_index.while | 89 |
| abstract_inverted_index.(KPIs) | 25 |
| abstract_inverted_index.causes | 3 |
| abstract_inverted_index.expert | 31, 70 |
| abstract_inverted_index.gains. | 193 |
| abstract_inverted_index.kernel | 22 |
| abstract_inverted_index.labels | 38, 88, 149 |
| abstract_inverted_index.mobile | 12 |
| abstract_inverted_index.purely | 50 |
| abstract_inverted_index.recent | 170 |
| abstract_inverted_index.robust | 73 |
| abstract_inverted_index.scale, | 40 |
| abstract_inverted_index.scarce | 147 |
| abstract_inverted_index.steps, | 122 |
| abstract_inverted_index.strong | 127 |
| abstract_inverted_index.supply | 100 |
| abstract_inverted_index.DK-Root | 76, 165 |
| abstract_inverted_index.Quality | 5 |
| abstract_inverted_index.address | 54 |
| abstract_inverted_index.complex | 18 |
| abstract_inverted_index.confirm | 175 |
| abstract_inverted_index.dataset | 160 |
| abstract_inverted_index.design, | 186 |
| abstract_inverted_index.encoder | 80, 138 |
| abstract_inverted_index.improve | 130 |
| abstract_inverted_index.jointly | 144 |
| abstract_inverted_index.precise | 69 |
| abstract_inverted_index.propose | 57 |
| abstract_inverted_index.quality | 190 |
| abstract_inverted_index.reverse | 120 |
| abstract_inverted_index.sharpen | 151 |
| abstract_inverted_index.through | 94 |
| abstract_inverted_index.unifies | 64 |
| abstract_inverted_index.Although | 33 |
| abstract_inverted_index.DK-Root, | 58 |
| abstract_inverted_index.Finally, | 136 |
| abstract_inverted_index.abundant | 86 |
| abstract_inverted_index.accuracy | 48 |
| abstract_inverted_index.decision | 152 |
| abstract_inverted_index.generate | 37 |
| abstract_inverted_index.guidance | 71 |
| abstract_inverted_index.learning | 84 |
| abstract_inverted_index.limiting | 46 |
| abstract_inverted_index.methods. | 173 |
| abstract_inverted_index.networks | 13 |
| abstract_inverted_index.produces | 124 |
| abstract_inverted_index.reliable | 30 |
| abstract_inverted_index.scalable | 65 |
| abstract_inverted_index.scarcity | 28 |
| abstract_inverted_index.Ablations | 174 |
| abstract_inverted_index.Extensive | 154 |
| abstract_inverted_index.accuracy, | 163 |
| abstract_inverted_index.analysis. | 75 |
| abstract_inverted_index.denoising | 91 |
| abstract_inverted_index.diffusion | 108, 121, 181 |
| abstract_inverted_index.framework | 62 |
| abstract_inverted_index.generates | 111 |
| abstract_inverted_index.introduce | 105 |
| abstract_inverted_index.necessity | 177 |
| abstract_inverted_index.pretrains | 78 |
| abstract_inverted_index.sequences | 113 |
| abstract_inverted_index.Diagnosing | 0 |
| abstract_inverted_index.Experience | 7 |
| abstract_inverted_index.classifier | 142 |
| abstract_inverted_index.explicitly | 90 |
| abstract_inverted_index.fine-tuned | 145 |
| abstract_inverted_index.heuristics | 35 |
| abstract_inverted_index.indicators | 24 |
| abstract_inverted_index.objective. | 98 |
| abstract_inverted_index.preserving | 114 |
| abstract_inverted_index.root-cause | 74, 115 |
| abstract_inverted_index.rule-based | 34, 87 |
| abstract_inverted_index.semantics, | 116 |
| abstract_inverted_index.supervised | 96 |
| abstract_inverted_index.surpassing | 166 |
| abstract_inverted_index.validating | 187 |
| abstract_inverted_index.approaches. | 52 |
| abstract_inverted_index.boundaries. | 153 |
| abstract_inverted_index.challenging | 15 |
| abstract_inverted_index.compactness | 132 |
| abstract_inverted_index.conditional | 180 |
| abstract_inverted_index.contrastive | 82, 97 |
| abstract_inverted_index.controlling | 119 |
| abstract_inverted_index.cross-layer | 19 |
| abstract_inverted_index.data-driven | 51 |
| abstract_inverted_index.demonstrate | 161 |
| abstract_inverted_index.experiments | 155 |
| abstract_inverted_index.inter-class | 134 |
| abstract_inverted_index.intra-class | 131 |
| abstract_inverted_index.lightweight | 141 |
| abstract_inverted_index.operational | 11 |
| abstract_inverted_index.performance | 23 |
| abstract_inverted_index.real-world, | 158 |
| abstract_inverted_index.supervision | 67 |
| abstract_inverted_index.time-series | 172 |
| abstract_inverted_index.traditional | 167 |
| abstract_inverted_index.annotations. | 32 |
| abstract_inverted_index.augmentation | 182 |
| abstract_inverted_index.degradations | 9 |
| abstract_inverted_index.interactions | 20 |
| abstract_inverted_index.augmentation, | 103 |
| abstract_inverted_index.augmentations | 128 |
| abstract_inverted_index.separability. | 135 |
| abstract_inverted_index.task-faithful | 101 |
| abstract_inverted_index.classification | 192 |
| abstract_inverted_index.operator-grade | 159 |
| abstract_inverted_index.representation | 83, 189 |
| abstract_inverted_index.coarse-grained, | 45 |
| abstract_inverted_index.expert-verified | 148 |
| abstract_inverted_index.semi-supervised | 171 |
| abstract_inverted_index.state-of-the-art | 162 |
| abstract_inverted_index.class-conditional | 107 |
| abstract_inverted_index.pretrain-finetune | 185 |
| abstract_inverted_index.data-and-knowledge-driven | 61 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 8 |
| citation_normalized_percentile |