Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data Article Swipe

PDF

Cheng-Hao Tu , Hong-You Chen , Zheda Mai , Jike Zhong , Vardaan Pahuja , Tanya Berger‐Wolf , Song Gao , Charles V. Stewart , Yu Su , Wei‐Lun Chao ·

YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2311.01420

We propose a learning problem involving adapting a pre-trained source model to the target domain for classifying all classes that appeared in the source data, using target data that covers only a partial label space. This problem is practical, as it is unrealistic for the target end-users to collect data for all classes prior to adaptation. However, it has received limited attention in the literature. To shed light on this issue, we construct benchmark datasets and conduct extensive experiments to uncover the inherent challenges. We found a dilemma -- on the one hand, adapting to the new target domain is important to claim better performance; on the other hand, we observe that preserving the classification accuracy of classes missing in the target adaptation data is highly challenging, let alone improving them. To tackle this, we identify two key directions: 1) disentangling domain gradients from classification gradients, and 2) preserving class relationships. We present several effective solutions that maintain the accuracy of the missing classes and enhance the overall performance, establishing solid baselines for holistic transfer of pre-trained models with partial target data.

Related Topics

Computer Science

Benchmark (Surveying)

Machine Learning

Artificial Intelligence

Mathematical Analysis

Physics

Optics

Geodesy

Concepts

Computer science Benchmark (surveying) Transfer of learning Domain (mathematical analysis) Domain adaptation Machine learning Class (philosophy) Artificial intelligence Adaptation (eye) Construct (python library) Key (lock) Labeled data Missing data Space (punctuation) Data mining Mathematics Programming language Geography Operating system Computer security Classifier (UML) Mathematical analysis Physics Optics Geodesy

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2311.01420
PDF: https://arxiv.org/pdf/2311.01420
OA Status: green
Cited By: 1
Related Works: 10
OpenAlex ID: https://openalex.org/W4388327648

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4388327648

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2311.01420

Digital Object Identifier
Title: Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2023

Year of publication
Publication date: 2023-11-02

Full publication date if available
Authors: Cheng-Hao Tu, Hong-You Chen, Zheda Mai, Jike Zhong, Vardaan Pahuja, Tanya Berger‐Wolf, Song Gao, Charles V. Stewart, Yu Su, Wei‐Lun Chao

List of authors in order
Landing page: https://arxiv.org/abs/2311.01420

Publisher landing page
PDF URL: https://arxiv.org/pdf/2311.01420

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: green

Open access status per OpenAlex
OA URL: https://arxiv.org/pdf/2311.01420

Direct OA link when available
Concepts: Computer science, Benchmark (surveying), Transfer of learning, Domain (mathematical analysis), Domain adaptation, Machine learning, Class (philosophy), Artificial intelligence, Adaptation (eye), Construct (python library), Key (lock), Labeled data, Missing data, Space (punctuation), Data mining, Mathematics, Programming language, Geography, Operating system, Computer security, Classifier (UML), Mathematical analysis, Physics, Optics, Geodesy

Top concepts (fields/topics) attached by OpenAlex
Cited by: 1

Total citation count in OpenAlex
Citations by year (recent): 2024: 1

Per-year citation counts (last 5 years)
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4388327648
doi	https://doi.org/10.48550/arxiv.2311.01420
ids.doi	https://doi.org/10.48550/arxiv.2311.01420
ids.openalex	https://openalex.org/W4388327648
fwci
type	preprint
title	Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
biblio.issue
biblio.volume
biblio.last_page
biblio.first_page
topics[0].id	https://openalex.org/T11307
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	0.9980999827384949
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	Domain Adaptation and Few-Shot Learning
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.7943126559257507
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C185798385
concepts[1].level	2
concepts[1].score	0.7363783717155457
concepts[1].wikidata	https://www.wikidata.org/wiki/Q1161707
concepts[1].display_name	Benchmark (surveying)
concepts[2].id	https://openalex.org/C150899416
concepts[2].level	2
concepts[2].score	0.6189095377922058
concepts[2].wikidata	https://www.wikidata.org/wiki/Q1820378
concepts[2].display_name	Transfer of learning
concepts[3].id	https://openalex.org/C36503486
concepts[3].level	2
concepts[3].score	0.6057873964309692
concepts[3].wikidata	https://www.wikidata.org/wiki/Q11235244
concepts[3].display_name	Domain (mathematical analysis)
concepts[4].id	https://openalex.org/C2776434776
concepts[4].level	3
concepts[4].score	0.5660004615783691
concepts[4].wikidata	https://www.wikidata.org/wiki/Q19246213
concepts[4].display_name	Domain adaptation
concepts[5].id	https://openalex.org/C119857082
concepts[5].level	1
concepts[5].score	0.5655527710914612
concepts[5].wikidata	https://www.wikidata.org/wiki/Q2539
concepts[5].display_name	Machine learning
concepts[6].id	https://openalex.org/C2777212361
concepts[6].level	2
concepts[6].score	0.5614446997642517
concepts[6].wikidata	https://www.wikidata.org/wiki/Q5127848
concepts[6].display_name	Class (philosophy)
concepts[7].id	https://openalex.org/C154945302
concepts[7].level	1
concepts[7].score	0.5459176898002625
concepts[7].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[7].display_name	Artificial intelligence
concepts[8].id	https://openalex.org/C139807058
concepts[8].level	2
concepts[8].score	0.5446634888648987
concepts[8].wikidata	https://www.wikidata.org/wiki/Q352374
concepts[8].display_name	Adaptation (eye)
concepts[9].id	https://openalex.org/C2780801425
concepts[9].level	2
concepts[9].score	0.5384262800216675
concepts[9].wikidata	https://www.wikidata.org/wiki/Q5164392
concepts[9].display_name	Construct (python library)
concepts[10].id	https://openalex.org/C26517878
concepts[10].level	2
concepts[10].score	0.46966660022735596
concepts[10].wikidata	https://www.wikidata.org/wiki/Q228039
concepts[10].display_name	Key (lock)
concepts[11].id	https://openalex.org/C2776145971
concepts[11].level	2
concepts[11].score	0.45352277159690857
concepts[11].wikidata	https://www.wikidata.org/wiki/Q30673951
concepts[11].display_name	Labeled data
concepts[12].id	https://openalex.org/C9357733
concepts[12].level	2
concepts[12].score	0.4339730441570282
concepts[12].wikidata	https://www.wikidata.org/wiki/Q6878417
concepts[12].display_name	Missing data
concepts[13].id	https://openalex.org/C2778572836
concepts[13].level	2
concepts[13].score	0.4122644066810608
concepts[13].wikidata	https://www.wikidata.org/wiki/Q380933
concepts[13].display_name	Space (punctuation)
concepts[14].id	https://openalex.org/C124101348
concepts[14].level	1
concepts[14].score	0.36784446239471436
concepts[14].wikidata	https://www.wikidata.org/wiki/Q172491
concepts[14].display_name	Data mining
concepts[15].id	https://openalex.org/C33923547
concepts[15].level	0
concepts[15].score	0.06548646092414856
concepts[15].wikidata	https://www.wikidata.org/wiki/Q395
concepts[15].display_name	Mathematics
concepts[16].id	https://openalex.org/C199360897
concepts[16].level	1
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q9143
concepts[16].display_name	Programming language
concepts[17].id	https://openalex.org/C205649164
concepts[17].level	0
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q1071
concepts[17].display_name	Geography
concepts[18].id	https://openalex.org/C111919701
concepts[18].level	1
concepts[18].score	0.0
concepts[18].wikidata	https://www.wikidata.org/wiki/Q9135
concepts[18].display_name	Operating system
concepts[19].id	https://openalex.org/C38652104
concepts[19].level	1
concepts[19].score	0.0
concepts[19].wikidata	https://www.wikidata.org/wiki/Q3510521
concepts[19].display_name	Computer security
concepts[20].id	https://openalex.org/C95623464
concepts[20].level	2
concepts[20].score	0.0
concepts[20].wikidata	https://www.wikidata.org/wiki/Q1096149
concepts[20].display_name	Classifier (UML)
concepts[21].id	https://openalex.org/C134306372
concepts[21].level	1
concepts[21].score	0.0
concepts[21].wikidata	https://www.wikidata.org/wiki/Q7754
concepts[21].display_name	Mathematical analysis
concepts[22].id	https://openalex.org/C121332964
concepts[22].level	0
concepts[22].score	0.0
concepts[22].wikidata	https://www.wikidata.org/wiki/Q413
concepts[22].display_name	Physics
concepts[23].id	https://openalex.org/C120665830
concepts[23].level	1
concepts[23].score	0.0
concepts[23].wikidata	https://www.wikidata.org/wiki/Q14620
concepts[23].display_name	Optics
concepts[24].id	https://openalex.org/C13280743
concepts[24].level	1
concepts[24].score	0.0
concepts[24].wikidata	https://www.wikidata.org/wiki/Q131089
concepts[24].display_name	Geodesy
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.7943126559257507
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/benchmark
keywords[1].score	0.7363783717155457
keywords[1].display_name	Benchmark (surveying)
keywords[2].id	https://openalex.org/keywords/transfer-of-learning
keywords[2].score	0.6189095377922058
keywords[2].display_name	Transfer of learning
keywords[3].id	https://openalex.org/keywords/domain
keywords[3].score	0.6057873964309692
keywords[3].display_name	Domain (mathematical analysis)
keywords[4].id	https://openalex.org/keywords/domain-adaptation
keywords[4].score	0.5660004615783691
keywords[4].display_name	Domain adaptation
keywords[5].id	https://openalex.org/keywords/machine-learning
keywords[5].score	0.5655527710914612
keywords[5].display_name	Machine learning
keywords[6].id	https://openalex.org/keywords/class
keywords[6].score	0.5614446997642517
keywords[6].display_name	Class (philosophy)
keywords[7].id	https://openalex.org/keywords/artificial-intelligence
keywords[7].score	0.5459176898002625
keywords[7].display_name	Artificial intelligence
keywords[8].id	https://openalex.org/keywords/adaptation
keywords[8].score	0.5446634888648987
keywords[8].display_name	Adaptation (eye)
keywords[9].id	https://openalex.org/keywords/construct
keywords[9].score	0.5384262800216675
keywords[9].display_name	Construct (python library)
keywords[10].id	https://openalex.org/keywords/key
keywords[10].score	0.46966660022735596
keywords[10].display_name	Key (lock)
keywords[11].id	https://openalex.org/keywords/labeled-data
keywords[11].score	0.45352277159690857
keywords[11].display_name	Labeled data
keywords[12].id	https://openalex.org/keywords/missing-data
keywords[12].score	0.4339730441570282
keywords[12].display_name	Missing data
keywords[13].id	https://openalex.org/keywords/space
keywords[13].score	0.4122644066810608
keywords[13].display_name	Space (punctuation)
keywords[14].id	https://openalex.org/keywords/data-mining
keywords[14].score	0.36784446239471436
keywords[14].display_name	Data mining
keywords[15].id	https://openalex.org/keywords/mathematics
keywords[15].score	0.06548646092414856
keywords[15].display_name	Mathematics
language	en
locations[0].id	pmh:oai:arXiv.org:2311.01420
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/2311.01420
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/2311.01420
locations[1].id	doi:10.48550/arxiv.2311.01420
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.2311.01420
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5077935756
authorships[0].author.orcid	https://orcid.org/0000-0002-3168-7963
authorships[0].author.display_name	Cheng-Hao Tu
authorships[0].author_position	first
authorships[0].raw_author_name	Tu, Cheng-Hao
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5012764388
authorships[1].author.orcid	https://orcid.org/0000-0002-8127-5588
authorships[1].author.display_name	Hong-You Chen
authorships[1].author_position	middle
authorships[1].raw_author_name	Chen, Hong-You
authorships[1].is_corresponding	False
authorships[2].author.id	https://openalex.org/A5066572795
authorships[2].author.orcid	https://orcid.org/0000-0003-3703-563X
authorships[2].author.display_name	Zheda Mai
authorships[2].author_position	middle
authorships[2].raw_author_name	Mai, Zheda
authorships[2].is_corresponding	False
authorships[3].author.id	https://openalex.org/A5088198600
authorships[3].author.orcid
authorships[3].author.display_name	Jike Zhong
authorships[3].author_position	middle
authorships[3].raw_author_name	Zhong, Jike
authorships[3].is_corresponding	False
authorships[4].author.id	https://openalex.org/A5102752724
authorships[4].author.orcid	https://orcid.org/0000-0001-7538-8474
authorships[4].author.display_name	Vardaan Pahuja
authorships[4].author_position	middle
authorships[4].raw_author_name	Pahuja, Vardaan
authorships[4].is_corresponding	False
authorships[5].author.id	https://openalex.org/A5060005215
authorships[5].author.orcid	https://orcid.org/0000-0001-7610-1412
authorships[5].author.display_name	Tanya Berger‐Wolf
authorships[5].author_position	middle
authorships[5].raw_author_name	Berger-Wolf, Tanya
authorships[5].is_corresponding	False
authorships[6].author.id	https://openalex.org/A5007542519
authorships[6].author.orcid	https://orcid.org/0000-0001-7427-6681
authorships[6].author.display_name	Song Gao
authorships[6].author_position	middle
authorships[6].raw_author_name	Gao, Song
authorships[6].is_corresponding	False
authorships[7].author.id	https://openalex.org/A5035964079
authorships[7].author.orcid	https://orcid.org/0000-0001-6532-6675
authorships[7].author.display_name	Charles V. Stewart
authorships[7].author_position	middle
authorships[7].raw_author_name	Stewart, Charles
authorships[7].is_corresponding	False
authorships[8].author.id	https://openalex.org/A5101639173
authorships[8].author.orcid	https://orcid.org/0000-0001-9350-8361
authorships[8].author.display_name	Yu Su
authorships[8].author_position	middle
authorships[8].raw_author_name	Su, Yu
authorships[8].is_corresponding	False
authorships[9].author.id	https://openalex.org/A5101520942
authorships[9].author.orcid	https://orcid.org/0000-0003-1269-7231
authorships[9].author.display_name	Wei‐Lun Chao
authorships[9].author_position	last
authorships[9].raw_author_name	Chao, Wei-Lun
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/2311.01420
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2023-11-04T00:00:00
display_name	Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data
has_fulltext	False
is_retracted	False
updated_date	2025-11-06T06:51:31.235846
primary_topic.id	https://openalex.org/T11307
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	0.9980999827384949
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	Domain Adaptation and Few-Shot Learning
related_works	https://openalex.org/W3095487414, https://openalex.org/W2901026139, https://openalex.org/W3035557009, https://openalex.org/W3204418343, https://openalex.org/W2341113105, https://openalex.org/W2955172689, https://openalex.org/W3132602785, https://openalex.org/W3046182208, https://openalex.org/W2343346879, https://openalex.org/W2186589590
cited_by_count	1
counts_by_year[0].year	2024
counts_by_year[0].cited_by_count	1
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2311.01420
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/2311.01420
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/2311.01420
primary_location.id	pmh:oai:arXiv.org:2311.01420
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/2311.01420
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/2311.01420
publication_date	2023-11-02
publication_year	2023
referenced_works_count	0
abstract_inverted_index.a	2, 7, 31, 86
abstract_inverted_index.--	88
abstract_inverted_index.1)	139
abstract_inverted_index.2)	147
abstract_inverted_index.To	65, 131
abstract_inverted_index.We	0, 84, 151
abstract_inverted_index.as	39
abstract_inverted_index.in	21, 62, 119
abstract_inverted_index.is	37, 41, 99, 124
abstract_inverted_index.it	40, 57
abstract_inverted_index.of	116, 160, 175
abstract_inverted_index.on	68, 89, 105
abstract_inverted_index.to	11, 47, 54, 79, 94, 101
abstract_inverted_index.we	71, 109, 134
abstract_inverted_index.all	17, 51
abstract_inverted_index.and	75, 146, 164
abstract_inverted_index.for	15, 43, 50, 172
abstract_inverted_index.has	58
abstract_inverted_index.key	137
abstract_inverted_index.let	127
abstract_inverted_index.new	96
abstract_inverted_index.one	91
abstract_inverted_index.the	12, 22, 44, 63, 81, 90, 95, 106, 113, 120, 158, 161, 166
abstract_inverted_index.two	136
abstract_inverted_index.This	35
abstract_inverted_index.data	27, 49, 123
abstract_inverted_index.from	143
abstract_inverted_index.only	30
abstract_inverted_index.shed	66
abstract_inverted_index.that	19, 28, 111, 156
abstract_inverted_index.this	69
abstract_inverted_index.with	178
abstract_inverted_index.alone	128
abstract_inverted_index.claim	102
abstract_inverted_index.class	149
abstract_inverted_index.data,	24
abstract_inverted_index.data.	181
abstract_inverted_index.found	85
abstract_inverted_index.hand,	92, 108
abstract_inverted_index.label	33
abstract_inverted_index.light	67
abstract_inverted_index.model	10
abstract_inverted_index.other	107
abstract_inverted_index.prior	53
abstract_inverted_index.solid	170
abstract_inverted_index.them.	130
abstract_inverted_index.this,	133
abstract_inverted_index.using	25
abstract_inverted_index.better	103
abstract_inverted_index.covers	29
abstract_inverted_index.domain	14, 98, 141
abstract_inverted_index.highly	125
abstract_inverted_index.issue,	70
abstract_inverted_index.models	177
abstract_inverted_index.source	9, 23
abstract_inverted_index.space.	34
abstract_inverted_index.tackle	132
abstract_inverted_index.target	13, 26, 45, 97, 121, 180
abstract_inverted_index.classes	18, 52, 117, 163
abstract_inverted_index.collect	48
abstract_inverted_index.conduct	76
abstract_inverted_index.dilemma	87
abstract_inverted_index.enhance	165
abstract_inverted_index.limited	60
abstract_inverted_index.missing	118, 162
abstract_inverted_index.observe	110
abstract_inverted_index.overall	167
abstract_inverted_index.partial	32, 179
abstract_inverted_index.present	152
abstract_inverted_index.problem	4, 36
abstract_inverted_index.propose	1
abstract_inverted_index.several	153
abstract_inverted_index.uncover	80
abstract_inverted_index.However,	56
abstract_inverted_index.accuracy	115, 159
abstract_inverted_index.adapting	6, 93
abstract_inverted_index.appeared	20
abstract_inverted_index.datasets	74
abstract_inverted_index.holistic	173
abstract_inverted_index.identify	135
abstract_inverted_index.inherent	82
abstract_inverted_index.learning	3
abstract_inverted_index.maintain	157
abstract_inverted_index.received	59
abstract_inverted_index.transfer	174
abstract_inverted_index.attention	61
abstract_inverted_index.baselines	171
abstract_inverted_index.benchmark	73
abstract_inverted_index.construct	72
abstract_inverted_index.effective	154
abstract_inverted_index.end-users	46
abstract_inverted_index.extensive	77
abstract_inverted_index.gradients	142
abstract_inverted_index.important	100
abstract_inverted_index.improving	129
abstract_inverted_index.involving	5
abstract_inverted_index.solutions	155
abstract_inverted_index.adaptation	122
abstract_inverted_index.gradients,	145
abstract_inverted_index.practical,	38
abstract_inverted_index.preserving	112, 148
abstract_inverted_index.adaptation.	55
abstract_inverted_index.challenges.	83
abstract_inverted_index.classifying	16
abstract_inverted_index.directions:	138
abstract_inverted_index.experiments	78
abstract_inverted_index.literature.	64
abstract_inverted_index.pre-trained	8, 176
abstract_inverted_index.unrealistic	42
abstract_inverted_index.challenging,	126
abstract_inverted_index.establishing	169
abstract_inverted_index.performance,	168
abstract_inverted_index.performance;	104
abstract_inverted_index.disentangling	140
abstract_inverted_index.classification	114, 144
abstract_inverted_index.relationships.	150
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	10
citation_normalized_percentile