KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning Article Swipe
Fangchen Yu
,
Rizhen Hu
,
Yidong Lin
,
Yuqi Ma
,
Zhenghao Huang
,
Wenye Li
·
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.00420
YOU?
·
· 2024
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2501.00420
The Kolmogorov-Arnold Network (KAN) has recently gained attention as an alternative to traditional multi-layer perceptrons (MLPs), offering improved accuracy and interpretability by employing learnable activation functions on edges. In this paper, we introduce the Kolmogorov-Arnold Auto-Encoder (KAE), which integrates KAN with autoencoders (AEs) to enhance representation learning for retrieval, classification, and denoising tasks. Leveraging the flexible polynomial functions in KAN layers, KAE captures complex data patterns and non-linear relationships. Experiments on benchmark datasets demonstrate that KAE improves latent representation quality, reduces reconstruction errors, and achieves superior performance in downstream tasks such as retrieval, classification, and denoising, compared to standard autoencoders and other KAN variants. These results suggest KAE's potential as a useful tool for representation learning. Our code is available at \url{https://github.com/SciYu/KAE/}.
Related Topics
Concepts
Metadata
- Type
- preprint
- Language
- en
- Landing Page
- http://arxiv.org/abs/2501.00420
- https://arxiv.org/pdf/2501.00420
- OA Status
- green
- Related Works
- 10
- OpenAlex ID
- https://openalex.org/W4406031361
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4406031361Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2501.00420Digital Object Identifier
- Title
-
KAE: Kolmogorov-Arnold Auto-Encoder for Representation LearningWork title
- Type
-
preprintOpenAlex work type
- Language
-
enPrimary language
- Publication year
-
2024Year of publication
- Publication date
-
2024-12-31Full publication date if available
- Authors
-
Fangchen Yu, Rizhen Hu, Yidong Lin, Yuqi Ma, Zhenghao Huang, Wenye LiList of authors in order
- Landing page
-
https://arxiv.org/abs/2501.00420Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2501.00420Direct 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/2501.00420Direct OA link when available
- Concepts
-
Representation (politics), Encoder, Computer science, Autoencoder, Artificial intelligence, Deep learning, Political science, Law, Operating system, PoliticsTop 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/W4406031361 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2501.00420 |
| ids.doi | https://doi.org/10.48550/arxiv.2501.00420 |
| ids.openalex | https://openalex.org/W4406031361 |
| fwci | |
| type | preprint |
| title | KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning |
| 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 | 0.9789000153541565 |
| 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/C2776359362 |
| concepts[0].level | 3 |
| concepts[0].score | 0.680962324142456 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q2145286 |
| concepts[0].display_name | Representation (politics) |
| concepts[1].id | https://openalex.org/C118505674 |
| concepts[1].level | 2 |
| concepts[1].score | 0.5558120012283325 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q42586063 |
| concepts[1].display_name | Encoder |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.5044924020767212 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C101738243 |
| concepts[3].level | 3 |
| concepts[3].score | 0.4801561236381531 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q786435 |
| concepts[3].display_name | Autoencoder |
| concepts[4].id | https://openalex.org/C154945302 |
| concepts[4].level | 1 |
| concepts[4].score | 0.4377850294113159 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[4].display_name | Artificial intelligence |
| concepts[5].id | https://openalex.org/C108583219 |
| concepts[5].level | 2 |
| concepts[5].score | 0.15896883606910706 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[5].display_name | Deep learning |
| concepts[6].id | https://openalex.org/C17744445 |
| concepts[6].level | 0 |
| concepts[6].score | 0.06879320740699768 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q36442 |
| concepts[6].display_name | Political science |
| concepts[7].id | https://openalex.org/C199539241 |
| concepts[7].level | 1 |
| concepts[7].score | 0.04383784532546997 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q7748 |
| concepts[7].display_name | Law |
| concepts[8].id | https://openalex.org/C111919701 |
| concepts[8].level | 1 |
| concepts[8].score | 0.0 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q9135 |
| concepts[8].display_name | Operating system |
| concepts[9].id | https://openalex.org/C94625758 |
| concepts[9].level | 2 |
| concepts[9].score | 0.0 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q7163 |
| concepts[9].display_name | Politics |
| keywords[0].id | https://openalex.org/keywords/representation |
| keywords[0].score | 0.680962324142456 |
| keywords[0].display_name | Representation (politics) |
| keywords[1].id | https://openalex.org/keywords/encoder |
| keywords[1].score | 0.5558120012283325 |
| keywords[1].display_name | Encoder |
| keywords[2].id | https://openalex.org/keywords/computer-science |
| keywords[2].score | 0.5044924020767212 |
| keywords[2].display_name | Computer science |
| keywords[3].id | https://openalex.org/keywords/autoencoder |
| keywords[3].score | 0.4801561236381531 |
| keywords[3].display_name | Autoencoder |
| keywords[4].id | https://openalex.org/keywords/artificial-intelligence |
| keywords[4].score | 0.4377850294113159 |
| keywords[4].display_name | Artificial intelligence |
| keywords[5].id | https://openalex.org/keywords/deep-learning |
| keywords[5].score | 0.15896883606910706 |
| keywords[5].display_name | Deep learning |
| keywords[6].id | https://openalex.org/keywords/political-science |
| keywords[6].score | 0.06879320740699768 |
| keywords[6].display_name | Political science |
| keywords[7].id | https://openalex.org/keywords/law |
| keywords[7].score | 0.04383784532546997 |
| keywords[7].display_name | Law |
| language | en |
| locations[0].id | pmh:oai:arXiv.org:2501.00420 |
| 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/2501.00420 |
| 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/2501.00420 |
| locations[1].id | doi:10.48550/arxiv.2501.00420 |
| 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.2501.00420 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5015454078 |
| authorships[0].author.orcid | https://orcid.org/0000-0002-1256-2719 |
| authorships[0].author.display_name | Fangchen Yu |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yu, Fangchen |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5043064566 |
| authorships[1].author.orcid | https://orcid.org/0009-0000-3812-1252 |
| authorships[1].author.display_name | Rizhen Hu |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Hu, Ruilizhen |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5041059015 |
| authorships[2].author.orcid | https://orcid.org/0000-0001-7552-5555 |
| authorships[2].author.display_name | Yidong Lin |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Lin, Yidong |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5102209314 |
| authorships[3].author.orcid | |
| authorships[3].author.display_name | Yuqi Ma |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Ma, Yuqi |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5030229805 |
| authorships[4].author.orcid | https://orcid.org/0000-0001-5848-2012 |
| authorships[4].author.display_name | Zhenghao Huang |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Huang, Zhenghao |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5112937484 |
| authorships[5].author.orcid | https://orcid.org/0000-0003-2767-8498 |
| authorships[5].author.display_name | Wenye Li |
| authorships[5].author_position | last |
| authorships[5].raw_author_name | Li, Wenye |
| authorships[5].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/2501.00420 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-10-10T00:00:00 |
| display_name | KAE: Kolmogorov-Arnold Auto-Encoder for Representation Learning |
| 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 | 0.9789000153541565 |
| 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/W3013693939, https://openalex.org/W2566616303, https://openalex.org/W2159052453, https://openalex.org/W3131327266, https://openalex.org/W2734887215, https://openalex.org/W2803255133, https://openalex.org/W4220775285 |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2501.00420 |
| 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/2501.00420 |
| 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/2501.00420 |
| primary_location.id | pmh:oai:arXiv.org:2501.00420 |
| 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/2501.00420 |
| 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/2501.00420 |
| publication_date | 2024-12-31 |
| publication_year | 2024 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 110 |
| abstract_inverted_index.In | 28 |
| abstract_inverted_index.an | 9 |
| abstract_inverted_index.as | 8, 91, 109 |
| abstract_inverted_index.at | 120 |
| abstract_inverted_index.by | 21 |
| abstract_inverted_index.in | 58, 87 |
| abstract_inverted_index.is | 118 |
| abstract_inverted_index.on | 26, 70 |
| abstract_inverted_index.to | 11, 43, 97 |
| abstract_inverted_index.we | 31 |
| abstract_inverted_index.KAE | 61, 75 |
| abstract_inverted_index.KAN | 39, 59, 102 |
| abstract_inverted_index.Our | 116 |
| abstract_inverted_index.The | 0 |
| abstract_inverted_index.and | 19, 50, 66, 83, 94, 100 |
| abstract_inverted_index.for | 47, 113 |
| abstract_inverted_index.has | 4 |
| abstract_inverted_index.the | 33, 54 |
| abstract_inverted_index.code | 117 |
| abstract_inverted_index.data | 64 |
| abstract_inverted_index.such | 90 |
| abstract_inverted_index.that | 74 |
| abstract_inverted_index.this | 29 |
| abstract_inverted_index.tool | 112 |
| abstract_inverted_index.with | 40 |
| abstract_inverted_index.(AEs) | 42 |
| abstract_inverted_index.(KAN) | 3 |
| abstract_inverted_index.KAE's | 107 |
| abstract_inverted_index.These | 104 |
| abstract_inverted_index.other | 101 |
| abstract_inverted_index.tasks | 89 |
| abstract_inverted_index.which | 37 |
| abstract_inverted_index.(KAE), | 36 |
| abstract_inverted_index.edges. | 27 |
| abstract_inverted_index.gained | 6 |
| abstract_inverted_index.latent | 77 |
| abstract_inverted_index.paper, | 30 |
| abstract_inverted_index.tasks. | 52 |
| abstract_inverted_index.useful | 111 |
| abstract_inverted_index.(MLPs), | 15 |
| abstract_inverted_index.Network | 2 |
| abstract_inverted_index.complex | 63 |
| abstract_inverted_index.enhance | 44 |
| abstract_inverted_index.errors, | 82 |
| abstract_inverted_index.layers, | 60 |
| abstract_inverted_index.reduces | 80 |
| abstract_inverted_index.results | 105 |
| abstract_inverted_index.suggest | 106 |
| abstract_inverted_index.accuracy | 18 |
| abstract_inverted_index.achieves | 84 |
| abstract_inverted_index.captures | 62 |
| abstract_inverted_index.compared | 96 |
| abstract_inverted_index.datasets | 72 |
| abstract_inverted_index.flexible | 55 |
| abstract_inverted_index.improved | 17 |
| abstract_inverted_index.improves | 76 |
| abstract_inverted_index.learning | 46 |
| abstract_inverted_index.offering | 16 |
| abstract_inverted_index.patterns | 65 |
| abstract_inverted_index.quality, | 79 |
| abstract_inverted_index.recently | 5 |
| abstract_inverted_index.standard | 98 |
| abstract_inverted_index.superior | 85 |
| abstract_inverted_index.attention | 7 |
| abstract_inverted_index.available | 119 |
| abstract_inverted_index.benchmark | 71 |
| abstract_inverted_index.denoising | 51 |
| abstract_inverted_index.employing | 22 |
| abstract_inverted_index.functions | 25, 57 |
| abstract_inverted_index.introduce | 32 |
| abstract_inverted_index.learnable | 23 |
| abstract_inverted_index.learning. | 115 |
| abstract_inverted_index.potential | 108 |
| abstract_inverted_index.variants. | 103 |
| abstract_inverted_index.Leveraging | 53 |
| abstract_inverted_index.activation | 24 |
| abstract_inverted_index.denoising, | 95 |
| abstract_inverted_index.downstream | 88 |
| abstract_inverted_index.integrates | 38 |
| abstract_inverted_index.non-linear | 67 |
| abstract_inverted_index.polynomial | 56 |
| abstract_inverted_index.retrieval, | 48, 92 |
| abstract_inverted_index.Experiments | 69 |
| abstract_inverted_index.alternative | 10 |
| abstract_inverted_index.demonstrate | 73 |
| abstract_inverted_index.multi-layer | 13 |
| abstract_inverted_index.perceptrons | 14 |
| abstract_inverted_index.performance | 86 |
| abstract_inverted_index.traditional | 12 |
| abstract_inverted_index.Auto-Encoder | 35 |
| abstract_inverted_index.autoencoders | 41, 99 |
| abstract_inverted_index.reconstruction | 81 |
| abstract_inverted_index.relationships. | 68 |
| abstract_inverted_index.representation | 45, 78, 114 |
| abstract_inverted_index.classification, | 49, 93 |
| abstract_inverted_index.interpretability | 20 |
| abstract_inverted_index.Kolmogorov-Arnold | 1, 34 |
| abstract_inverted_index.\url{https://github.com/SciYu/KAE/}. | 121 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 6 |
| citation_normalized_percentile |