LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Class Article Swipe
H. Zhu
,
Angelo Cangelosi
,
Procheta Sen
,
Anirbit Mukherjee
·
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.04856
YOU?
·
· 2023
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2310.04856
In this work, we instantiate a novel perturbation-based multi-class explanation framework, LIPEx (Locally Interpretable Probabilistic Explanation). We demonstrate that LIPEx not only locally replicates the probability distributions output by the widely used complex classification models but also provides insight into how every feature deemed to be important affects the prediction probability for each of the possible classes. We achieve this by defining the explanation as a matrix obtained via regression with respect to the Hellinger distance in the space of probability distributions. Ablation tests on text and image data, show that LIPEx-guided removal of important features from the data causes more change in predictions for the underlying model than similar tests based on other saliency-based or feature importance-based Explainable AI (XAI) methods. It is also shown that compared to LIME, LIPEx is more data efficient in terms of using a lesser number of perturbations of the data to obtain a reliable explanation. This data-efficiency is seen to manifest as LIPEx being able to compute its explanation matrix around 53% faster than all-class LIME, for classification experiments with text data.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2310.04856
- https://arxiv.org/pdf/2310.04856
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4387559460
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4387559460Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2310.04856Digital Object Identifier
- Title
-
LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True ClassWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2023Year of publication
- Publication date
-
2023-10-07Full publication date if available
- Authors
-
H. Zhu, Angelo Cangelosi, Procheta Sen, Anirbit MukherjeeList of authors in order
- Landing page
-
https://arxiv.org/abs/2310.04856Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2310.04856Direct 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/2310.04856Direct OA link when available
- Concepts
-
Probabilistic logic, Feature (linguistics), Class (philosophy), Artificial intelligence, Hellinger distance, Computer science, Mathematics, Pattern recognition (psychology), Feature vector, Machine learning, Statistics, Philosophy, LinguisticsTop 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/W4387559460 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2310.04856 |
| ids.doi | https://doi.org/10.48550/arxiv.2310.04856 |
| ids.openalex | https://openalex.org/W4387559460 |
| fwci | |
| type | preprint |
| title | LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Class |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12026 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.9988999962806702 |
| 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 | Explainable Artificial Intelligence (XAI) |
| topics[1].id | https://openalex.org/T11689 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.9794999957084656 |
| 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 | Adversarial Robustness in Machine Learning |
| topics[2].id | https://openalex.org/T11512 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9671000242233276 |
| 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 | Anomaly Detection Techniques and Applications |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C49937458 |
| concepts[0].level | 2 |
| concepts[0].score | 0.6849435567855835 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q2599292 |
| concepts[0].display_name | Probabilistic logic |
| concepts[1].id | https://openalex.org/C2776401178 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5201181173324585 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[1].display_name | Feature (linguistics) |
| concepts[2].id | https://openalex.org/C2777212361 |
| concepts[2].level | 2 |
| concepts[2].score | 0.5062243342399597 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q5127848 |
| concepts[2].display_name | Class (philosophy) |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.504665732383728 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C153024298 |
| concepts[4].level | 2 |
| concepts[4].score | 0.5032555460929871 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q3030678 |
| concepts[4].display_name | Hellinger distance |
| concepts[5].id | https://openalex.org/C41008148 |
| concepts[5].level | 0 |
| concepts[5].score | 0.4881921410560608 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[5].display_name | Computer science |
| concepts[6].id | https://openalex.org/C33923547 |
| concepts[6].level | 0 |
| concepts[6].score | 0.44950684905052185 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q395 |
| concepts[6].display_name | Mathematics |
| concepts[7].id | https://openalex.org/C153180895 |
| concepts[7].level | 2 |
| concepts[7].score | 0.4245811402797699 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[7].display_name | Pattern recognition (psychology) |
| concepts[8].id | https://openalex.org/C83665646 |
| concepts[8].level | 2 |
| concepts[8].score | 0.4230457544326782 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q42139305 |
| concepts[8].display_name | Feature vector |
| concepts[9].id | https://openalex.org/C119857082 |
| concepts[9].level | 1 |
| concepts[9].score | 0.37784889340400696 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[9].display_name | Machine learning |
| concepts[10].id | https://openalex.org/C105795698 |
| concepts[10].level | 1 |
| concepts[10].score | 0.2544228732585907 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q12483 |
| concepts[10].display_name | Statistics |
| concepts[11].id | https://openalex.org/C138885662 |
| concepts[11].level | 0 |
| concepts[11].score | 0.0 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q5891 |
| concepts[11].display_name | Philosophy |
| concepts[12].id | https://openalex.org/C41895202 |
| concepts[12].level | 1 |
| concepts[12].score | 0.0 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q8162 |
| concepts[12].display_name | Linguistics |
| keywords[0].id | https://openalex.org/keywords/probabilistic-logic |
| keywords[0].score | 0.6849435567855835 |
| keywords[0].display_name | Probabilistic logic |
| keywords[1].id | https://openalex.org/keywords/feature |
| keywords[1].score | 0.5201181173324585 |
| keywords[1].display_name | Feature (linguistics) |
| keywords[2].id | https://openalex.org/keywords/class |
| keywords[2].score | 0.5062243342399597 |
| keywords[2].display_name | Class (philosophy) |
| keywords[3].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[3].score | 0.504665732383728 |
| keywords[3].display_name | Artificial intelligence |
| keywords[4].id | https://openalex.org/keywords/hellinger-distance |
| keywords[4].score | 0.5032555460929871 |
| keywords[4].display_name | Hellinger distance |
| keywords[5].id | https://openalex.org/keywords/computer-science |
| keywords[5].score | 0.4881921410560608 |
| keywords[5].display_name | Computer science |
| keywords[6].id | https://openalex.org/keywords/mathematics |
| keywords[6].score | 0.44950684905052185 |
| keywords[6].display_name | Mathematics |
| keywords[7].id | https://openalex.org/keywords/pattern-recognition |
| keywords[7].score | 0.4245811402797699 |
| keywords[7].display_name | Pattern recognition (psychology) |
| keywords[8].id | https://openalex.org/keywords/feature-vector |
| keywords[8].score | 0.4230457544326782 |
| keywords[8].display_name | Feature vector |
| keywords[9].id | https://openalex.org/keywords/machine-learning |
| keywords[9].score | 0.37784889340400696 |
| keywords[9].display_name | Machine learning |
| keywords[10].id | https://openalex.org/keywords/statistics |
| keywords[10].score | 0.2544228732585907 |
| keywords[10].display_name | Statistics |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2310.04856 |
| 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/2310.04856 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | |
| 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/2310.04856 |
| locations[1].id | doi:10.48550/arxiv.2310.04856 |
| 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.2310.04856 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100757520 |
| authorships[0].author.orcid | https://orcid.org/0000-0001-8066-7048 |
| authorships[0].author.display_name | H. Zhu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Zhu, Hongbo |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5091768977 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-4709-2243 |
| authorships[1].author.display_name | Angelo Cangelosi |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Cangelosi, Angelo |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5000569823 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-3814-5462 |
| authorships[2].author.display_name | Procheta Sen |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Sen, Procheta |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5084835559 |
| authorships[3].author.orcid | https://orcid.org/0000-0001-5189-8939 |
| authorships[3].author.display_name | Anirbit Mukherjee |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Mukherjee, Anirbit |
| authorships[3].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/2310.04856 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | LIPEx-Locally Interpretable Probabilistic Explanations-To Look Beyond The True Class |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12026 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.9988999962806702 |
| 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 | Explainable Artificial Intelligence (XAI) |
| related_works | https://openalex.org/W2050620380, https://openalex.org/W1977834563, https://openalex.org/W1979265735, https://openalex.org/W4390831585, https://openalex.org/W2057424919, https://openalex.org/W3097851170, https://openalex.org/W4385216087, https://openalex.org/W3157595377, https://openalex.org/W4301399849, https://openalex.org/W1182612369 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2310.04856 |
| 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/2310.04856 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | |
| 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/2310.04856 |
| primary_location.id | pmh:oai:arXiv.org:2310.04856 |
| 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/2310.04856 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | |
| 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/2310.04856 |
| publication_date | 2023-10-07 |
| publication_year | 2023 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 5, 65, 139, 149 |
| abstract_inverted_index.AI | 119 |
| abstract_inverted_index.In | 0 |
| abstract_inverted_index.It | 122 |
| abstract_inverted_index.We | 16, 57 |
| abstract_inverted_index.as | 64, 158 |
| abstract_inverted_index.be | 45 |
| abstract_inverted_index.by | 28, 60 |
| abstract_inverted_index.in | 76, 102, 135 |
| abstract_inverted_index.is | 123, 131, 154 |
| abstract_inverted_index.of | 53, 79, 93, 137, 142, 144 |
| abstract_inverted_index.on | 84, 112 |
| abstract_inverted_index.or | 115 |
| abstract_inverted_index.to | 44, 72, 128, 147, 156, 162 |
| abstract_inverted_index.we | 3 |
| abstract_inverted_index.53% | 168 |
| abstract_inverted_index.and | 86 |
| abstract_inverted_index.but | 35 |
| abstract_inverted_index.for | 51, 104, 173 |
| abstract_inverted_index.how | 40 |
| abstract_inverted_index.its | 164 |
| abstract_inverted_index.not | 20 |
| abstract_inverted_index.the | 24, 29, 48, 54, 62, 73, 77, 97, 105, 145 |
| abstract_inverted_index.via | 68 |
| abstract_inverted_index.This | 152 |
| abstract_inverted_index.able | 161 |
| abstract_inverted_index.also | 36, 124 |
| abstract_inverted_index.data | 98, 133, 146 |
| abstract_inverted_index.each | 52 |
| abstract_inverted_index.from | 96 |
| abstract_inverted_index.into | 39 |
| abstract_inverted_index.more | 100, 132 |
| abstract_inverted_index.only | 21 |
| abstract_inverted_index.seen | 155 |
| abstract_inverted_index.show | 89 |
| abstract_inverted_index.text | 85, 177 |
| abstract_inverted_index.than | 108, 170 |
| abstract_inverted_index.that | 18, 90, 126 |
| abstract_inverted_index.this | 1, 59 |
| abstract_inverted_index.used | 31 |
| abstract_inverted_index.with | 70, 176 |
| abstract_inverted_index.(XAI) | 120 |
| abstract_inverted_index.LIME, | 129, 172 |
| abstract_inverted_index.LIPEx | 11, 19, 130, 159 |
| abstract_inverted_index.based | 111 |
| abstract_inverted_index.being | 160 |
| abstract_inverted_index.data, | 88 |
| abstract_inverted_index.data. | 178 |
| abstract_inverted_index.every | 41 |
| abstract_inverted_index.image | 87 |
| abstract_inverted_index.model | 107 |
| abstract_inverted_index.novel | 6 |
| abstract_inverted_index.other | 113 |
| abstract_inverted_index.shown | 125 |
| abstract_inverted_index.space | 78 |
| abstract_inverted_index.terms | 136 |
| abstract_inverted_index.tests | 83, 110 |
| abstract_inverted_index.using | 138 |
| abstract_inverted_index.work, | 2 |
| abstract_inverted_index.around | 167 |
| abstract_inverted_index.causes | 99 |
| abstract_inverted_index.change | 101 |
| abstract_inverted_index.deemed | 43 |
| abstract_inverted_index.faster | 169 |
| abstract_inverted_index.lesser | 140 |
| abstract_inverted_index.matrix | 66, 166 |
| abstract_inverted_index.models | 34 |
| abstract_inverted_index.number | 141 |
| abstract_inverted_index.obtain | 148 |
| abstract_inverted_index.output | 27 |
| abstract_inverted_index.widely | 30 |
| abstract_inverted_index.achieve | 58 |
| abstract_inverted_index.affects | 47 |
| abstract_inverted_index.complex | 32 |
| abstract_inverted_index.compute | 163 |
| abstract_inverted_index.feature | 42, 116 |
| abstract_inverted_index.insight | 38 |
| abstract_inverted_index.locally | 22 |
| abstract_inverted_index.removal | 92 |
| abstract_inverted_index.respect | 71 |
| abstract_inverted_index.similar | 109 |
| abstract_inverted_index.(Locally | 12 |
| abstract_inverted_index.Ablation | 82 |
| abstract_inverted_index.classes. | 56 |
| abstract_inverted_index.compared | 127 |
| abstract_inverted_index.defining | 61 |
| abstract_inverted_index.distance | 75 |
| abstract_inverted_index.features | 95 |
| abstract_inverted_index.manifest | 157 |
| abstract_inverted_index.methods. | 121 |
| abstract_inverted_index.obtained | 67 |
| abstract_inverted_index.possible | 55 |
| abstract_inverted_index.provides | 37 |
| abstract_inverted_index.reliable | 150 |
| abstract_inverted_index.Hellinger | 74 |
| abstract_inverted_index.all-class | 171 |
| abstract_inverted_index.efficient | 134 |
| abstract_inverted_index.important | 46, 94 |
| abstract_inverted_index.framework, | 10 |
| abstract_inverted_index.prediction | 49 |
| abstract_inverted_index.regression | 69 |
| abstract_inverted_index.replicates | 23 |
| abstract_inverted_index.underlying | 106 |
| abstract_inverted_index.Explainable | 118 |
| abstract_inverted_index.demonstrate | 17 |
| abstract_inverted_index.experiments | 175 |
| abstract_inverted_index.explanation | 9, 63, 165 |
| abstract_inverted_index.instantiate | 4 |
| abstract_inverted_index.multi-class | 8 |
| abstract_inverted_index.predictions | 103 |
| abstract_inverted_index.probability | 25, 50, 80 |
| abstract_inverted_index.LIPEx-guided | 91 |
| abstract_inverted_index.explanation. | 151 |
| abstract_inverted_index.Explanation). | 15 |
| abstract_inverted_index.Interpretable | 13 |
| abstract_inverted_index.Probabilistic | 14 |
| abstract_inverted_index.distributions | 26 |
| abstract_inverted_index.perturbations | 143 |
| abstract_inverted_index.classification | 33, 174 |
| abstract_inverted_index.distributions. | 81 |
| abstract_inverted_index.saliency-based | 114 |
| abstract_inverted_index.data-efficiency | 153 |
| abstract_inverted_index.importance-based | 117 |
| abstract_inverted_index.perturbation-based | 7 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| citation_normalized_percentile |