Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries Article Swipe
Kun-Peng Ning
,
Lue Tao
,
Songcan Chen
,
Sheng-Jun Huang
·
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2103.14824
YOU?
·
· 2021
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2103.14824
In addition to high accuracy, robustness is becoming increasingly important for machine learning models in various applications. Recently, much research has been devoted to improving the model robustness by training with noise perturbations. Most existing studies assume a fixed perturbation level for all training examples, which however hardly holds in real tasks. In fact, excessive perturbations may destroy the discriminative content of an example, while deficient perturbations may fail to provide helpful information for improving the robustness. Motivated by this observation, we propose to adaptively adjust the perturbation levels for each example in the training process. Specifically, a novel active learning framework is proposed to allow the model to interactively query the correct perturbation level from human experts. By designing a cost-effective sampling strategy along with a new query type, the robustness can be significantly improved with a few queries. Both theoretical analysis and experimental studies validate the effectiveness of the proposed approach.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2103.14824
- https://arxiv.org/pdf/2103.14824
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W3173818476
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W3173818476Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2103.14824Digital Object Identifier
- Title
-
Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active QueriesWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2021Year of publication
- Publication date
-
2021-03-27Full publication date if available
- Authors
-
Kun-Peng Ning, Lue Tao, Songcan Chen, Sheng-Jun HuangList of authors in order
- Landing page
-
https://arxiv.org/abs/2103.14824Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2103.14824Direct 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/2103.14824Direct OA link when available
- Concepts
-
Robustness (evolution), Computer science, Perturbation (astronomy), Discriminative model, Machine learning, Artificial intelligence, Physics, Biochemistry, Chemistry, Gene, Quantum mechanicsTop 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/W3173818476 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2103.14824 |
| ids.doi | https://doi.org/10.48550/arxiv.2103.14824 |
| ids.mag | 3173818476 |
| ids.openalex | https://openalex.org/W3173818476 |
| fwci | |
| type | preprint |
| title | Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| topics[0].id | https://openalex.org/T12072 |
| topics[0].field.id | https://openalex.org/fields/17 |
| topics[0].field.display_name | Computer Science |
| topics[0].score | 0.996399998664856 |
| 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 and Algorithms |
| topics[1].id | https://openalex.org/T12535 |
| topics[1].field.id | https://openalex.org/fields/17 |
| topics[1].field.display_name | Computer Science |
| topics[1].score | 0.989799976348877 |
| 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 | Machine Learning and Data Classification |
| topics[2].id | https://openalex.org/T12761 |
| topics[2].field.id | https://openalex.org/fields/17 |
| topics[2].field.display_name | Computer Science |
| topics[2].score | 0.9876000285148621 |
| 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 | Data Stream Mining Techniques |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C63479239 |
| concepts[0].level | 3 |
| concepts[0].score | 0.779542863368988 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q7353546 |
| concepts[0].display_name | Robustness (evolution) |
| concepts[1].id | https://openalex.org/C41008148 |
| concepts[1].level | 0 |
| concepts[1].score | 0.7133647203445435 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[1].display_name | Computer science |
| concepts[2].id | https://openalex.org/C177918212 |
| concepts[2].level | 2 |
| concepts[2].score | 0.6351022124290466 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q803623 |
| concepts[2].display_name | Perturbation (astronomy) |
| concepts[3].id | https://openalex.org/C97931131 |
| concepts[3].level | 2 |
| concepts[3].score | 0.6319751739501953 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q5282087 |
| concepts[3].display_name | Discriminative model |
| concepts[4].id | https://openalex.org/C119857082 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4227333962917328 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[4].display_name | Machine learning |
| concepts[5].id | https://openalex.org/C154945302 |
| concepts[5].level | 1 |
| concepts[5].score | 0.36810508370399475 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[5].display_name | Artificial intelligence |
| concepts[6].id | https://openalex.org/C121332964 |
| concepts[6].level | 0 |
| concepts[6].score | 0.0 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q413 |
| concepts[6].display_name | Physics |
| concepts[7].id | https://openalex.org/C55493867 |
| concepts[7].level | 1 |
| concepts[7].score | 0.0 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7094 |
| concepts[7].display_name | Biochemistry |
| concepts[8].id | https://openalex.org/C185592680 |
| concepts[8].level | 0 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q2329 |
| concepts[8].display_name | Chemistry |
| concepts[9].id | https://openalex.org/C104317684 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7187 |
| concepts[9].display_name | Gene |
| concepts[10].id | https://openalex.org/C62520636 |
| concepts[10].level | 1 |
| concepts[10].score | 0.0 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q944 |
| concepts[10].display_name | Quantum mechanics |
| keywords[0].id | https://openalex.org/keywords/robustness |
| keywords[0].score | 0.779542863368988 |
| keywords[0].display_name | Robustness (evolution) |
| keywords[1].id | https://openalex.org/keywords/computer-science |
| keywords[1].score | 0.7133647203445435 |
| keywords[1].display_name | Computer science |
| keywords[2].id | https://openalex.org/keywords/perturbation |
| keywords[2].score | 0.6351022124290466 |
| keywords[2].display_name | Perturbation (astronomy) |
| keywords[3].id | https://openalex.org/keywords/discriminative-model |
| keywords[3].score | 0.6319751739501953 |
| keywords[3].display_name | Discriminative model |
| keywords[4].id | https://openalex.org/keywords/machine-learning |
| keywords[4].score | 0.4227333962917328 |
| keywords[4].display_name | Machine learning |
| keywords[5].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[5].score | 0.36810508370399475 |
| keywords[5].display_name | Artificial intelligence |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2103.14824 |
| 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/2103.14824 |
| 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/2103.14824 |
| locations[1].id | doi:10.48550/arxiv.2103.14824 |
| 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 | cc-by |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | https://openalex.org/licenses/cc-by |
| 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.2103.14824 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5056432762 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-8249-9911 |
| authorships[0].author.display_name | Kun-Peng Ning |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Kun-Peng Ning |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5049073944 |
| authorships[1].author.orcid | |
| authorships[1].author.display_name | Lue Tao |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Lue Tao |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5101596072 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-5164-0070 |
| authorships[2].author.display_name | Songcan Chen |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Songcan Chen |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5103204774 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-7673-5367 |
| authorships[3].author.display_name | Sheng-Jun Huang |
| authorships[3].author_position | last |
| authorships[3].raw_author_name | Sheng-Jun Huang |
| 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/2103.14824 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2021-07-05T00:00:00 |
| display_name | Improving Model Robustness by Adaptively Correcting Perturbation Levels with Active Queries |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-06T06:51:31.235846 |
| primary_topic.id | https://openalex.org/T12072 |
| primary_topic.field.id | https://openalex.org/fields/17 |
| primary_topic.field.display_name | Computer Science |
| primary_topic.score | 0.996399998664856 |
| 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 and Algorithms |
| related_works | https://openalex.org/W2961085424, https://openalex.org/W4306674287, https://openalex.org/W3046775127, https://openalex.org/W3107602296, https://openalex.org/W3170094116, https://openalex.org/W4386462264, https://openalex.org/W4364306694, https://openalex.org/W4312192474, https://openalex.org/W4283697347, https://openalex.org/W4210805261 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2103.14824 |
| 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/2103.14824 |
| 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/2103.14824 |
| primary_location.id | pmh:oai:arXiv.org:2103.14824 |
| 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/2103.14824 |
| 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/2103.14824 |
| publication_date | 2021-03-27 |
| publication_year | 2021 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 37, 97, 120, 126, 137 |
| abstract_inverted_index.By | 118 |
| abstract_inverted_index.In | 0, 52 |
| abstract_inverted_index.an | 62 |
| abstract_inverted_index.be | 133 |
| abstract_inverted_index.by | 28, 78 |
| abstract_inverted_index.in | 14, 49, 92 |
| abstract_inverted_index.is | 6, 102 |
| abstract_inverted_index.of | 61, 149 |
| abstract_inverted_index.to | 2, 23, 69, 83, 104, 108 |
| abstract_inverted_index.we | 81 |
| abstract_inverted_index.all | 42 |
| abstract_inverted_index.and | 143 |
| abstract_inverted_index.can | 132 |
| abstract_inverted_index.few | 138 |
| abstract_inverted_index.for | 10, 41, 73, 89 |
| abstract_inverted_index.has | 20 |
| abstract_inverted_index.may | 56, 67 |
| abstract_inverted_index.new | 127 |
| abstract_inverted_index.the | 25, 58, 75, 86, 93, 106, 111, 130, 147, 150 |
| abstract_inverted_index.Both | 140 |
| abstract_inverted_index.Most | 33 |
| abstract_inverted_index.been | 21 |
| abstract_inverted_index.each | 90 |
| abstract_inverted_index.fail | 68 |
| abstract_inverted_index.from | 115 |
| abstract_inverted_index.high | 3 |
| abstract_inverted_index.much | 18 |
| abstract_inverted_index.real | 50 |
| abstract_inverted_index.this | 79 |
| abstract_inverted_index.with | 30, 125, 136 |
| abstract_inverted_index.allow | 105 |
| abstract_inverted_index.along | 124 |
| abstract_inverted_index.fact, | 53 |
| abstract_inverted_index.fixed | 38 |
| abstract_inverted_index.holds | 48 |
| abstract_inverted_index.human | 116 |
| abstract_inverted_index.level | 40, 114 |
| abstract_inverted_index.model | 26, 107 |
| abstract_inverted_index.noise | 31 |
| abstract_inverted_index.novel | 98 |
| abstract_inverted_index.query | 110, 128 |
| abstract_inverted_index.type, | 129 |
| abstract_inverted_index.which | 45 |
| abstract_inverted_index.while | 64 |
| abstract_inverted_index.active | 99 |
| abstract_inverted_index.adjust | 85 |
| abstract_inverted_index.assume | 36 |
| abstract_inverted_index.hardly | 47 |
| abstract_inverted_index.levels | 88 |
| abstract_inverted_index.models | 13 |
| abstract_inverted_index.tasks. | 51 |
| abstract_inverted_index.content | 60 |
| abstract_inverted_index.correct | 112 |
| abstract_inverted_index.destroy | 57 |
| abstract_inverted_index.devoted | 22 |
| abstract_inverted_index.example | 91 |
| abstract_inverted_index.helpful | 71 |
| abstract_inverted_index.however | 46 |
| abstract_inverted_index.machine | 11 |
| abstract_inverted_index.propose | 82 |
| abstract_inverted_index.provide | 70 |
| abstract_inverted_index.studies | 35, 145 |
| abstract_inverted_index.various | 15 |
| abstract_inverted_index.addition | 1 |
| abstract_inverted_index.analysis | 142 |
| abstract_inverted_index.becoming | 7 |
| abstract_inverted_index.example, | 63 |
| abstract_inverted_index.existing | 34 |
| abstract_inverted_index.experts. | 117 |
| abstract_inverted_index.improved | 135 |
| abstract_inverted_index.learning | 12, 100 |
| abstract_inverted_index.process. | 95 |
| abstract_inverted_index.proposed | 103, 151 |
| abstract_inverted_index.queries. | 139 |
| abstract_inverted_index.research | 19 |
| abstract_inverted_index.sampling | 122 |
| abstract_inverted_index.strategy | 123 |
| abstract_inverted_index.training | 29, 43, 94 |
| abstract_inverted_index.validate | 146 |
| abstract_inverted_index.Motivated | 77 |
| abstract_inverted_index.Recently, | 17 |
| abstract_inverted_index.accuracy, | 4 |
| abstract_inverted_index.approach. | 152 |
| abstract_inverted_index.deficient | 65 |
| abstract_inverted_index.designing | 119 |
| abstract_inverted_index.examples, | 44 |
| abstract_inverted_index.excessive | 54 |
| abstract_inverted_index.framework | 101 |
| abstract_inverted_index.important | 9 |
| abstract_inverted_index.improving | 24, 74 |
| abstract_inverted_index.adaptively | 84 |
| abstract_inverted_index.robustness | 5, 27, 131 |
| abstract_inverted_index.information | 72 |
| abstract_inverted_index.robustness. | 76 |
| abstract_inverted_index.theoretical | 141 |
| abstract_inverted_index.experimental | 144 |
| abstract_inverted_index.increasingly | 8 |
| abstract_inverted_index.observation, | 80 |
| abstract_inverted_index.perturbation | 39, 87, 113 |
| abstract_inverted_index.Specifically, | 96 |
| abstract_inverted_index.applications. | 16 |
| abstract_inverted_index.effectiveness | 148 |
| abstract_inverted_index.interactively | 109 |
| abstract_inverted_index.perturbations | 55, 66 |
| abstract_inverted_index.significantly | 134 |
| abstract_inverted_index.cost-effective | 121 |
| abstract_inverted_index.discriminative | 59 |
| abstract_inverted_index.perturbations. | 32 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 4 |
| sustainable_development_goals[0].id | https://metadata.un.org/sdg/10 |
| sustainable_development_goals[0].score | 0.7200000286102295 |
| sustainable_development_goals[0].display_name | Reduced inequalities |
| citation_normalized_percentile |