A Comprehensive Survey on Self-Interpretable Neural Networks Article Swipe
Yang Ji
,
Ying Sun
,
Yuting Zhang
,
Zhigaoyuan Wang
,
Yuanxin Zhuang
,
Zheng Gong
,
Dazhong Shen
,
Chuan Qin
,
Hengshu Zhu
,
Wei-Hua Lin
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.15638
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.15638
Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Post-hoc interpretability, which provides explanations for pre-trained models, is often at risk of robustness and fidelity. This has inspired a rising interest in self-interpretable neural networks, which inherently reveal the prediction rationale through the model structures. Although there exist surveys on post-hoc interpretability, a comprehensive and systematic survey of self-interpretable neural networks is still missing. To address this gap, we first collect and review existing works on self-interpretable neural networks and provide a structured summary of their methodologies from five key perspectives: attribution-based, function-based, concept-based, prototype-based, and rule-based self-interpretation. We also present concrete, visualized examples of model explanations and discuss their applicability across diverse scenarios, including image, text, graph data, and deep reinforcement learning. Additionally, we summarize existing evaluation metrics for self-interpretability and identify open challenges in this field, offering insights for future research. To support ongoing developments, we present a publicly accessible resource to track advancements in this domain: https://github.com/yangji721/Awesome-Self-Interpretable-Neural-Network.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2501.15638
- https://arxiv.org/pdf/2501.15638
- OA Status
- green
- Cited By
- 2
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4406880973
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4406880973Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2501.15638Digital Object Identifier
- Title
-
A Comprehensive Survey on Self-Interpretable Neural NetworksWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2025Year of publication
- Publication date
-
2025-01-26Full publication date if available
- Authors
-
Yang Ji, Ying Sun, Yuting Zhang, Zhigaoyuan Wang, Yuanxin Zhuang, Zheng Gong, Dazhong Shen, Chuan Qin, Hengshu Zhu, Wei-Hua LinList of authors in order
- Landing page
-
https://arxiv.org/abs/2501.15638Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2501.15638Direct 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/2501.15638Direct OA link when available
- Concepts
-
Artificial neural network, Artificial intelligence, Deep neural networks, Computer science, Machine learning, Data scienceTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
2Total citation count in OpenAlex
- Citations by year (recent)
-
2025: 2Per-year citation counts (last 5 years)
- Related works (count)
-
10Other works algorithmically related by OpenAlex
Full payload
| id | https://openalex.org/W4406880973 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2501.15638 |
| ids.doi | https://doi.org/10.48550/arxiv.2501.15638 |
| ids.openalex | https://openalex.org/W4406880973 |
| fwci | |
| type | preprint |
| title | A Comprehensive Survey on Self-Interpretable Neural Networks |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T13702 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.8773000240325928 |
| 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 | Machine Learning in Healthcare |
| topics[1].id | https://openalex.org/T10320 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.8342999815940857 |
| 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 | Neural Networks and Applications |
| topics[2].id | https://openalex.org/T12026 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.8039000034332275 |
| topics[2].domain.id | https://openalex.org/domains/3 |
| topics[2].domain.display_name | Physical Sciences |
| topics[2].subfield.id | https://openalex.org/subfields/1702 |
| topics[2].subfield.display_name | Artificial Intelligence |
| topics[2].display_name | Explainable Artificial Intelligence (XAI) |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C50644808 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6176407933235168 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[0].display_name | Artificial neural network |
| concepts[1].id | https://openalex.org/C154945302 |
| concepts[1].level | 1 |
| concepts[1].score | 0.4987812042236328 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[1].display_name | Artificial intelligence |
| concepts[2].id | https://openalex.org/C2984842247 |
| concepts[2].level | 3 |
| concepts[2].score | 0.4206886291503906 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[2].display_name | Deep neural networks |
| concepts[3].id | https://openalex.org/C41008148 |
| concepts[3].level | 0 |
| concepts[3].score | 0.4128708839416504 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[3].display_name | Computer science |
| concepts[4].id | https://openalex.org/C119857082 |
| concepts[4].level | 1 |
| concepts[4].score | 0.344440221786499 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[4].display_name | Machine learning |
| concepts[5].id | https://openalex.org/C2522767166 |
| concepts[5].level | 1 |
| concepts[5].score | 0.325602650642395 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q2374463 |
| concepts[5].display_name | Data science |
| keywords[0].id | https://openalex.org/keywords/artificial-neural-network |
| keywords[0].score | 0.6176407933235168 |
| keywords[0].display_name | Artificial neural network |
| keywords[1].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[1].score | 0.4987812042236328 |
| keywords[1].display_name | Artificial intelligence |
| keywords[2].id | https://openalex.org/keywords/deep-neural-networks |
| keywords[2].score | 0.4206886291503906 |
| keywords[2].display_name | Deep neural networks |
| keywords[3].id | https://openalex.org/keywords/computer-science |
| keywords[3].score | 0.4128708839416504 |
| keywords[3].display_name | Computer science |
| keywords[4].id | https://openalex.org/keywords/machine-learning |
| keywords[4].score | 0.344440221786499 |
| keywords[4].display_name | Machine learning |
| keywords[5].id | https://openalex.org/keywords/data-science |
| keywords[5].score | 0.325602650642395 |
| keywords[5].display_name | Data science |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2501.15638 |
| 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/2501.15638 |
| 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/2501.15638 |
| locations[1].id | doi:10.48550/arxiv.2501.15638 |
| 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.2501.15638 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5102201336 |
| authorships[0].author.orcid | https://orcid.org/0009-0003-6867-8715 |
| authorships[0].author.display_name | Yang Ji |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Ji, Yang |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5046835504 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4763-6060 |
| authorships[1].author.display_name | Ying Sun |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Sun, Ying |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101931258 |
| authorships[2].author.orcid | https://orcid.org/0009-0006-0025-9479 |
| authorships[2].author.display_name | Yuting Zhang |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Zhang, Yuting |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5073907963 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Zhigaoyuan Wang |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Wang, Zhigaoyuan |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5028374467 |
| authorships[4].author.orcid | |
| authorships[4].author.display_name | Yuanxin Zhuang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Zhuang, Yuanxin |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5090899515 |
| authorships[5].author.orcid | https://orcid.org/0000-0001-7285-2630 |
| authorships[5].author.display_name | Zheng Gong |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Gong, Zheng |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5075007087 |
| authorships[6].author.orcid | https://orcid.org/0000-0002-3947-4153 |
| authorships[6].author.display_name | Dazhong Shen |
| authorships[6].author_position | middle |
| authorships[6].raw_author_name | Shen, Dazhong |
| authorships[6].is_corresponding | False |
| authorships[7].author.id | https://openalex.org/A5102883290 |
| authorships[7].author.orcid | https://orcid.org/0000-0002-5354-8630 |
| authorships[7].author.display_name | Chuan Qin |
| authorships[7].author_position | middle |
| authorships[7].raw_author_name | Qin, Chuan |
| authorships[7].is_corresponding | False |
| authorships[8].author.id | https://openalex.org/A5049015446 |
| authorships[8].author.orcid | https://orcid.org/0000-0003-4570-643X |
| authorships[8].author.display_name | Hengshu Zhu |
| authorships[8].author_position | middle |
| authorships[8].raw_author_name | Zhu, Hengshu |
| authorships[8].is_corresponding | False |
| authorships[9].author.id | https://openalex.org/A5101840304 |
| authorships[9].author.orcid | https://orcid.org/0009-0004-0533-9836 |
| authorships[9].author.display_name | Wei-Hua Lin |
| authorships[9].author_position | last |
| authorships[9].raw_author_name | Xiong, Hui |
| authorships[9].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/2501.15638 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-01-29T00:00:00 |
| display_name | A Comprehensive Survey on Self-Interpretable Neural Networks |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T13702 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.8773000240325928 |
| 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 | Machine Learning in Healthcare |
| related_works | https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W4387369504, https://openalex.org/W3046775127, https://openalex.org/W4394896187, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W3107602296, https://openalex.org/W4364306694, https://openalex.org/W4312192474 |
| cited_by_count | 2 |
| counts_by_year[0].year | 2025 |
| counts_by_year[0].cited_by_count | 2 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2501.15638 |
| 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/2501.15638 |
| 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/2501.15638 |
| primary_location.id | pmh:oai:arXiv.org:2501.15638 |
| 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/2501.15638 |
| 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/2501.15638 |
| publication_date | 2025-01-26 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 42, 66, 95, 163 |
| abstract_inverted_index.To | 78, 157 |
| abstract_inverted_index.We | 112 |
| abstract_inverted_index.at | 33 |
| abstract_inverted_index.in | 19, 45, 149, 170 |
| abstract_inverted_index.is | 31, 75 |
| abstract_inverted_index.of | 12, 35, 71, 98, 118 |
| abstract_inverted_index.on | 63, 89 |
| abstract_inverted_index.to | 167 |
| abstract_inverted_index.we | 82, 138, 161 |
| abstract_inverted_index.and | 37, 68, 85, 93, 109, 121, 133, 145 |
| abstract_inverted_index.for | 28, 143, 154 |
| abstract_inverted_index.has | 40 |
| abstract_inverted_index.key | 103 |
| abstract_inverted_index.the | 10, 52, 56 |
| abstract_inverted_index.This | 39 |
| abstract_inverted_index.also | 113 |
| abstract_inverted_index.deep | 134 |
| abstract_inverted_index.five | 102 |
| abstract_inverted_index.from | 101 |
| abstract_inverted_index.gap, | 81 |
| abstract_inverted_index.have | 2 |
| abstract_inverted_index.lack | 11 |
| abstract_inverted_index.open | 147 |
| abstract_inverted_index.risk | 34 |
| abstract_inverted_index.this | 80, 150, 171 |
| abstract_inverted_index.use, | 17 |
| abstract_inverted_index.data, | 132 |
| abstract_inverted_index.exist | 61 |
| abstract_inverted_index.first | 83 |
| abstract_inverted_index.graph | 131 |
| abstract_inverted_index.model | 57, 119 |
| abstract_inverted_index.often | 32 |
| abstract_inverted_index.still | 76 |
| abstract_inverted_index.text, | 130 |
| abstract_inverted_index.their | 15, 99, 123 |
| abstract_inverted_index.there | 60 |
| abstract_inverted_index.track | 168 |
| abstract_inverted_index.which | 25, 49 |
| abstract_inverted_index.works | 88 |
| abstract_inverted_index.Neural | 0 |
| abstract_inverted_index.across | 6, 125 |
| abstract_inverted_index.field, | 151 |
| abstract_inverted_index.future | 155 |
| abstract_inverted_index.image, | 129 |
| abstract_inverted_index.limits | 14 |
| abstract_inverted_index.neural | 47, 73, 91 |
| abstract_inverted_index.reveal | 51 |
| abstract_inverted_index.review | 86 |
| abstract_inverted_index.rising | 43 |
| abstract_inverted_index.survey | 70 |
| abstract_inverted_index.address | 79 |
| abstract_inverted_index.collect | 84 |
| abstract_inverted_index.discuss | 122 |
| abstract_inverted_index.diverse | 126 |
| abstract_inverted_index.domain: | 172 |
| abstract_inverted_index.fields. | 8 |
| abstract_inverted_index.metrics | 142 |
| abstract_inverted_index.models, | 30 |
| abstract_inverted_index.ongoing | 159 |
| abstract_inverted_index.present | 114, 162 |
| abstract_inverted_index.provide | 94 |
| abstract_inverted_index.success | 5 |
| abstract_inverted_index.summary | 97 |
| abstract_inverted_index.support | 158 |
| abstract_inverted_index.surveys | 62 |
| abstract_inverted_index.through | 55 |
| abstract_inverted_index.various | 7 |
| abstract_inverted_index.Although | 59 |
| abstract_inverted_index.However, | 9 |
| abstract_inverted_index.Post-hoc | 23 |
| abstract_inverted_index.achieved | 3 |
| abstract_inverted_index.critical | 20 |
| abstract_inverted_index.examples | 117 |
| abstract_inverted_index.existing | 87, 140 |
| abstract_inverted_index.identify | 146 |
| abstract_inverted_index.insights | 153 |
| abstract_inverted_index.inspired | 41 |
| abstract_inverted_index.interest | 44 |
| abstract_inverted_index.missing. | 77 |
| abstract_inverted_index.networks | 1, 74, 92 |
| abstract_inverted_index.offering | 152 |
| abstract_inverted_index.post-hoc | 64 |
| abstract_inverted_index.provides | 26 |
| abstract_inverted_index.publicly | 164 |
| abstract_inverted_index.resource | 166 |
| abstract_inverted_index.concrete, | 115 |
| abstract_inverted_index.fidelity. | 38 |
| abstract_inverted_index.including | 128 |
| abstract_inverted_index.learning. | 136 |
| abstract_inverted_index.networks, | 48 |
| abstract_inverted_index.practical | 16 |
| abstract_inverted_index.rationale | 54 |
| abstract_inverted_index.research. | 156 |
| abstract_inverted_index.summarize | 139 |
| abstract_inverted_index.accessible | 165 |
| abstract_inverted_index.challenges | 148 |
| abstract_inverted_index.evaluation | 141 |
| abstract_inverted_index.inherently | 50 |
| abstract_inverted_index.prediction | 53 |
| abstract_inverted_index.remarkable | 4 |
| abstract_inverted_index.robustness | 36 |
| abstract_inverted_index.rule-based | 110 |
| abstract_inverted_index.scenarios, | 127 |
| abstract_inverted_index.scenarios. | 22 |
| abstract_inverted_index.structured | 96 |
| abstract_inverted_index.systematic | 69 |
| abstract_inverted_index.visualized | 116 |
| abstract_inverted_index.pre-trained | 29 |
| abstract_inverted_index.structures. | 58 |
| abstract_inverted_index.advancements | 169 |
| abstract_inverted_index.explanations | 27, 120 |
| abstract_inverted_index.particularly | 18 |
| abstract_inverted_index.Additionally, | 137 |
| abstract_inverted_index.applicability | 124 |
| abstract_inverted_index.comprehensive | 67 |
| abstract_inverted_index.developments, | 160 |
| abstract_inverted_index.methodologies | 100 |
| abstract_inverted_index.perspectives: | 104 |
| abstract_inverted_index.reinforcement | 135 |
| abstract_inverted_index.concept-based, | 107 |
| abstract_inverted_index.decision-making | 21 |
| abstract_inverted_index.function-based, | 106 |
| abstract_inverted_index.interpretability | 13 |
| abstract_inverted_index.prototype-based, | 108 |
| abstract_inverted_index.interpretability, | 24, 65 |
| abstract_inverted_index.attribution-based, | 105 |
| abstract_inverted_index.self-interpretable | 46, 72, 90 |
| abstract_inverted_index.self-interpretation. | 111 |
| abstract_inverted_index.self-interpretability | 144 |
| abstract_inverted_index.https://github.com/yangji721/Awesome-Self-Interpretable-Neural-Network. | 173 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 10 |
| citation_normalized_percentile |