Factor Graph-based Interpretable Neural Networks Article Swipe
Yicong Li
,
Kuanjiu Zhou
,
Shuo Yu
,
Qiang Zhang
,
Renqiang Luo
,
Xiaodong Li
,
Feng Xia
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2502.14572
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2502.14572
Comprehensible neural network explanations are foundations for a better understanding of decisions, especially when the input data are infused with malicious perturbations. Existing solutions generally mitigate the impact of perturbations through adversarial training, yet they fail to generate comprehensible explanations under unknown perturbations. To address this challenge, we propose AGAIN, a fActor GrAph-based Interpretable neural Network, which is capable of generating comprehensible explanations under unknown perturbations. Instead of retraining like previous solutions, the proposed AGAIN directly integrates logical rules by which logical errors in explanations are identified and rectified during inference. Specifically, we construct the factor graph to express logical rules between explanations and categories. By treating logical rules as exogenous knowledge, AGAIN can identify incomprehensible explanations that violate real-world logic. Furthermore, we propose an interactive intervention switch strategy rectifying explanations based on the logical guidance from the factor graph without learning perturbations, which overcomes the inherent limitation of adversarial training-based methods in defending only against known perturbations. Additionally, we theoretically demonstrate the effectiveness of employing factor graph by proving that the comprehensibility of explanations is strongly correlated with factor graph. Extensive experiments are conducted on three datasets and experimental results illustrate the superior performance of AGAIN compared to state-of-the-art baselines.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2502.14572
- https://arxiv.org/pdf/2502.14572
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4407806974
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4407806974Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2502.14572Digital Object Identifier
- Title
-
Factor Graph-based Interpretable Neural NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-02-20Full publication date if available
- Authors
-
Yicong Li, Kuanjiu Zhou, Shuo Yu, Qiang Zhang, Renqiang Luo, Xiaodong Li, Feng XiaList of authors in order
- Landing page
-
https://arxiv.org/abs/2502.14572Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2502.14572Direct 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/2502.14572Direct OA link when available
- Concepts
-
Computer science, Graph, Artificial intelligence, Artificial neural network, Factor (programming language), Theoretical computer science, Programming languageTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4407806974 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2502.14572 |
| ids.doi | https://doi.org/10.48550/arxiv.2502.14572 |
| ids.openalex | https://openalex.org/W4407806974 |
| fwci | |
| type | preprint |
| title | Factor Graph-based Interpretable Neural Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T10320 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.7746999859809875 |
| 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 | Neural Networks and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C41008148 |
| concepts[0].level | 0 |
| concepts[0].score | 0.5334515571594238 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[0].display_name | Computer science |
| concepts[1].id | https://openalex.org/C132525143 |
| concepts[1].level | 2 |
| concepts[1].score | 0.4977753460407257 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q141488 |
| concepts[1].display_name | Graph |
| concepts[2].id | https://openalex.org/C154945302 |
| concepts[2].level | 1 |
| concepts[2].score | 0.49265724420547485 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[2].display_name | Artificial intelligence |
| concepts[3].id | https://openalex.org/C50644808 |
| concepts[3].level | 2 |
| concepts[3].score | 0.4682772159576416 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[3].display_name | Artificial neural network |
| concepts[4].id | https://openalex.org/C2781039887 |
| concepts[4].level | 2 |
| concepts[4].score | 0.46172112226486206 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q1391724 |
| concepts[4].display_name | Factor (programming language) |
| concepts[5].id | https://openalex.org/C80444323 |
| concepts[5].level | 1 |
| concepts[5].score | 0.22142910957336426 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2878974 |
| concepts[5].display_name | Theoretical computer science |
| concepts[6].id | https://openalex.org/C199360897 |
| concepts[6].level | 1 |
| concepts[6].score | 0.0631818175315857 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q9143 |
| concepts[6].display_name | Programming language |
| keywords[0].id | https://openalex.org/keywords/computer-science |
| keywords[0].score | 0.5334515571594238 |
| keywords[0].display_name | Computer science |
| keywords[1].id | https://openalex.org/keywords/graph |
| keywords[1].score | 0.4977753460407257 |
| keywords[1].display_name | Graph |
| keywords[2].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[2].score | 0.49265724420547485 |
| keywords[2].display_name | Artificial intelligence |
| keywords[3].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[3].score | 0.4682772159576416 |
| keywords[3].display_name | Artificial neural network |
| keywords[4].id | https://openalex.org/keywords/factor |
| keywords[4].score | 0.46172112226486206 |
| keywords[4].display_name | Factor (programming language) |
| keywords[5].id | https://openalex.org/keywords/theoretical-computer-science |
| keywords[5].score | 0.22142910957336426 |
| keywords[5].display_name | Theoretical computer science |
| keywords[6].id | https://openalex.org/keywords/programming-language |
| keywords[6].score | 0.0631818175315857 |
| keywords[6].display_name | Programming language |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2502.14572 |
| 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/2502.14572 |
| 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/2502.14572 |
| locations[1].id | doi:10.48550/arxiv.2502.14572 |
| 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.2502.14572 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5053257302 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-7905-4885 |
| authorships[0].author.display_name | Yicong Li |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Li, Yicong |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101871892 |
| authorships[1].author.orcid | https://orcid.org/0000-0001-9437-9434 |
| authorships[1].author.display_name | Kuanjiu Zhou |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Zhou, Kuanjiu |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5004781883 |
| authorships[2].author.orcid | https://orcid.org/0000-0003-1124-9509 |
| authorships[2].author.display_name | Shuo Yu |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Yu, Shuo |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5100381999 |
| authorships[3].author.orcid | https://orcid.org/0000-0003-3776-9799 |
| authorships[3].author.display_name | Qiang Zhang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Zhang, Qiang |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5111184870 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Renqiang Luo |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Luo, Renqiang |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5100369719 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-0346-1526 |
| authorships[5].author.display_name | Xiaodong Li |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Li, Xiaodong |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5089615958 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-8324-1859 |
| authorships[6].author.display_name | Feng Xia |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Xia, Feng |
| authorships[6].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/2502.14572 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | Factor Graph-based Interpretable Neural Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T10320 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.7746999859809875 |
| 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 | Neural Networks and Applications |
| related_works | https://openalex.org/W4391375266, https://openalex.org/W2899084033, https://openalex.org/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W4391913857, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2502.14572 |
| 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/2502.14572 |
| 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/2502.14572 |
| primary_location.id | pmh:oai:arXiv.org:2502.14572 |
| 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/2502.14572 |
| 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/2502.14572 |
| publication_date | 2025-02-20 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 7, 50 |
| abstract_inverted_index.By | 105 |
| abstract_inverted_index.To | 43 |
| abstract_inverted_index.an | 124 |
| abstract_inverted_index.as | 109 |
| abstract_inverted_index.by | 79, 168 |
| abstract_inverted_index.in | 83, 152 |
| abstract_inverted_index.is | 57, 175 |
| abstract_inverted_index.of | 10, 28, 59, 67, 148, 164, 173, 195 |
| abstract_inverted_index.on | 132, 185 |
| abstract_inverted_index.to | 36, 97, 198 |
| abstract_inverted_index.we | 47, 92, 122, 159 |
| abstract_inverted_index.and | 87, 103, 188 |
| abstract_inverted_index.are | 4, 17, 85, 183 |
| abstract_inverted_index.can | 113 |
| abstract_inverted_index.for | 6 |
| abstract_inverted_index.the | 14, 26, 72, 94, 133, 137, 145, 162, 171, 192 |
| abstract_inverted_index.yet | 33 |
| abstract_inverted_index.data | 16 |
| abstract_inverted_index.fail | 35 |
| abstract_inverted_index.from | 136 |
| abstract_inverted_index.like | 69 |
| abstract_inverted_index.only | 154 |
| abstract_inverted_index.that | 117, 170 |
| abstract_inverted_index.they | 34 |
| abstract_inverted_index.this | 45 |
| abstract_inverted_index.when | 13 |
| abstract_inverted_index.with | 19, 178 |
| abstract_inverted_index.AGAIN | 74, 112, 196 |
| abstract_inverted_index.based | 131 |
| abstract_inverted_index.graph | 96, 139, 167 |
| abstract_inverted_index.input | 15 |
| abstract_inverted_index.known | 156 |
| abstract_inverted_index.rules | 78, 100, 108 |
| abstract_inverted_index.three | 186 |
| abstract_inverted_index.under | 40, 63 |
| abstract_inverted_index.which | 56, 80, 143 |
| abstract_inverted_index.AGAIN, | 49 |
| abstract_inverted_index.better | 8 |
| abstract_inverted_index.during | 89 |
| abstract_inverted_index.errors | 82 |
| abstract_inverted_index.fActor | 51 |
| abstract_inverted_index.factor | 95, 138, 166, 179 |
| abstract_inverted_index.graph. | 180 |
| abstract_inverted_index.impact | 27 |
| abstract_inverted_index.logic. | 120 |
| abstract_inverted_index.neural | 1, 54 |
| abstract_inverted_index.switch | 127 |
| abstract_inverted_index.Instead | 66 |
| abstract_inverted_index.address | 44 |
| abstract_inverted_index.against | 155 |
| abstract_inverted_index.between | 101 |
| abstract_inverted_index.capable | 58 |
| abstract_inverted_index.express | 98 |
| abstract_inverted_index.infused | 18 |
| abstract_inverted_index.logical | 77, 81, 99, 107, 134 |
| abstract_inverted_index.methods | 151 |
| abstract_inverted_index.network | 2 |
| abstract_inverted_index.propose | 48, 123 |
| abstract_inverted_index.proving | 169 |
| abstract_inverted_index.results | 190 |
| abstract_inverted_index.through | 30 |
| abstract_inverted_index.unknown | 41, 64 |
| abstract_inverted_index.violate | 118 |
| abstract_inverted_index.without | 140 |
| abstract_inverted_index.Existing | 22 |
| abstract_inverted_index.Network, | 55 |
| abstract_inverted_index.compared | 197 |
| abstract_inverted_index.datasets | 187 |
| abstract_inverted_index.directly | 75 |
| abstract_inverted_index.generate | 37 |
| abstract_inverted_index.guidance | 135 |
| abstract_inverted_index.identify | 114 |
| abstract_inverted_index.inherent | 146 |
| abstract_inverted_index.learning | 141 |
| abstract_inverted_index.mitigate | 25 |
| abstract_inverted_index.previous | 70 |
| abstract_inverted_index.proposed | 73 |
| abstract_inverted_index.strategy | 128 |
| abstract_inverted_index.strongly | 176 |
| abstract_inverted_index.superior | 193 |
| abstract_inverted_index.treating | 106 |
| abstract_inverted_index.Extensive | 181 |
| abstract_inverted_index.conducted | 184 |
| abstract_inverted_index.construct | 93 |
| abstract_inverted_index.defending | 153 |
| abstract_inverted_index.employing | 165 |
| abstract_inverted_index.exogenous | 110 |
| abstract_inverted_index.generally | 24 |
| abstract_inverted_index.malicious | 20 |
| abstract_inverted_index.overcomes | 144 |
| abstract_inverted_index.rectified | 88 |
| abstract_inverted_index.solutions | 23 |
| abstract_inverted_index.training, | 32 |
| abstract_inverted_index.baselines. | 200 |
| abstract_inverted_index.challenge, | 46 |
| abstract_inverted_index.correlated | 177 |
| abstract_inverted_index.decisions, | 11 |
| abstract_inverted_index.especially | 12 |
| abstract_inverted_index.generating | 60 |
| abstract_inverted_index.identified | 86 |
| abstract_inverted_index.illustrate | 191 |
| abstract_inverted_index.inference. | 90 |
| abstract_inverted_index.integrates | 76 |
| abstract_inverted_index.knowledge, | 111 |
| abstract_inverted_index.limitation | 147 |
| abstract_inverted_index.real-world | 119 |
| abstract_inverted_index.rectifying | 129 |
| abstract_inverted_index.retraining | 68 |
| abstract_inverted_index.solutions, | 71 |
| abstract_inverted_index.GrAph-based | 52 |
| abstract_inverted_index.adversarial | 31, 149 |
| abstract_inverted_index.categories. | 104 |
| abstract_inverted_index.demonstrate | 161 |
| abstract_inverted_index.experiments | 182 |
| abstract_inverted_index.foundations | 5 |
| abstract_inverted_index.interactive | 125 |
| abstract_inverted_index.performance | 194 |
| abstract_inverted_index.Furthermore, | 121 |
| abstract_inverted_index.experimental | 189 |
| abstract_inverted_index.explanations | 3, 39, 62, 84, 102, 116, 130, 174 |
| abstract_inverted_index.intervention | 126 |
| abstract_inverted_index.Additionally, | 158 |
| abstract_inverted_index.Interpretable | 53 |
| abstract_inverted_index.Specifically, | 91 |
| abstract_inverted_index.effectiveness | 163 |
| abstract_inverted_index.perturbations | 29 |
| abstract_inverted_index.theoretically | 160 |
| abstract_inverted_index.understanding | 9 |
| abstract_inverted_index.Comprehensible | 0 |
| abstract_inverted_index.comprehensible | 38, 61 |
| abstract_inverted_index.perturbations, | 142 |
| abstract_inverted_index.perturbations. | 21, 42, 65, 157 |
| abstract_inverted_index.training-based | 150 |
| abstract_inverted_index.incomprehensible | 115 |
| abstract_inverted_index.state-of-the-art | 199 |
| abstract_inverted_index.comprehensibility | 172 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |