Loss-Driven Channel Pruning of Convolutional Neural Networks Article Swipe

PDF

Xin Long , Xiangrong Zeng , Chen Chen , Huaxin Xiao , Maojun Zhang ·

YOU? · · 2020 · Open Access · · DOI: https://doi.org/10.1587/transinf.2019edl8200

The increase in computation cost and storage of convolutional neural networks (CNNs) severely hinders their applications on limited-resources devices in recent years. As a result, there is impending necessity to accelerate the networks by certain methods. In this paper, we propose a loss-driven method to prune redundant channels of CNNs. It identifies unimportant channels by using Taylor expansion technique regarding to scaling and shifting factors, and prunes those channels by fixed percentile threshold. By doing so, we obtain a compact network with less parameters and FLOPs consumption. In experimental section, we evaluate the proposed method in CIFAR datasets with several popular networks, including VGG-19, DenseNet-40 and ResNet-164, and experimental results demonstrate the proposed method is able to prune over 70% channels and parameters with no performance loss. Moreover, iterative pruning could be used to obtain more compact network.

Related Topics

Computer Science

Pruning

Convolutional Neural Network

Residual Neural Network

Algorithm

Artificial Intelligence

Concepts

Computer science Pruning FLOPS Convolutional neural network Computation Scaling Channel (broadcasting) Residual neural network Reduction (mathematics) Algorithm Artificial intelligence Pattern recognition (psychology) Computer network Parallel computing Mathematics Biology Agronomy Geometry

Metadata

Type: article
Language: en
Landing Page: https://doi.org/10.1587/transinf.2019edl8200
PDF: https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8200/_pdf
OA Status: diamond
Cited By: 2
References: 17
Related Works: 10
OpenAlex ID: https://openalex.org/W3022581078

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W3022581078

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.1587/transinf.2019edl8200

Digital Object Identifier
Title: Loss-Driven Channel Pruning of Convolutional Neural Networks

Work title
Type: article

OpenAlex work type
Language: en

Primary language
Publication year: 2020

Year of publication
Publication date: 2020-04-30

Full publication date if available
Authors: Xin Long, Xiangrong Zeng, Chen Chen, Huaxin Xiao, Maojun Zhang

List of authors in order
Landing page: https://doi.org/10.1587/transinf.2019edl8200

Publisher landing page
PDF URL: https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8200/_pdf

Direct link to full text PDF
Open access: Yes

Whether a free full text is available
OA status: diamond

Open access status per OpenAlex
OA URL: https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8200/_pdf

Direct OA link when available
Concepts: Computer science, Pruning, FLOPS, Convolutional neural network, Computation, Scaling, Channel (broadcasting), Residual neural network, Reduction (mathematics), Algorithm, Artificial intelligence, Pattern recognition (psychology), Computer network, Parallel computing, Mathematics, Biology, Agronomy, Geometry

Top concepts (fields/topics) attached by OpenAlex
Cited by: 2

Total citation count in OpenAlex
Citations by year (recent): 2021: 1, 2020: 1

Per-year citation counts (last 5 years)
References (count): 17

Number of works referenced by this work
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W3022581078
doi	https://doi.org/10.1587/transinf.2019edl8200
ids.doi	https://doi.org/10.1587/transinf.2019edl8200
ids.mag	3022581078
ids.openalex	https://openalex.org/W3022581078
fwci	0.20993464
type	article
title	Loss-Driven Channel Pruning of Convolutional Neural Networks
biblio.issue	5
biblio.volume	E103.D
biblio.last_page	1194
biblio.first_page	1190
topics[0].id	https://openalex.org/T10036
topics[0].field.id	https://openalex.org/fields/17
topics[0].field.display_name	Computer Science
topics[0].score	1.0
topics[0].domain.id	https://openalex.org/domains/3
topics[0].domain.display_name	Physical Sciences
topics[0].subfield.id	https://openalex.org/subfields/1707
topics[0].subfield.display_name	Computer Vision and Pattern Recognition
topics[0].display_name	Advanced Neural Network Applications
topics[1].id	https://openalex.org/T11307
topics[1].field.id	https://openalex.org/fields/17
topics[1].field.display_name	Computer Science
topics[1].score	0.9976999759674072
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	Domain Adaptation and Few-Shot Learning
topics[2].id	https://openalex.org/T10320
topics[2].field.id	https://openalex.org/fields/17
topics[2].field.display_name	Computer Science
topics[2].score	0.9927999973297119
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	Neural Networks and Applications
is_xpac	False
apc_list
apc_paid
concepts[0].id	https://openalex.org/C41008148
concepts[0].level	0
concepts[0].score	0.854586124420166
concepts[0].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[0].display_name	Computer science
concepts[1].id	https://openalex.org/C108010975
concepts[1].level	2
concepts[1].score	0.8315805196762085
concepts[1].wikidata	https://www.wikidata.org/wiki/Q500094
concepts[1].display_name	Pruning
concepts[2].id	https://openalex.org/C3826847
concepts[2].level	2
concepts[2].score	0.8306771516799927
concepts[2].wikidata	https://www.wikidata.org/wiki/Q188768
concepts[2].display_name	FLOPS
concepts[3].id	https://openalex.org/C81363708
concepts[3].level	2
concepts[3].score	0.7626126408576965
concepts[3].wikidata	https://www.wikidata.org/wiki/Q17084460
concepts[3].display_name	Convolutional neural network
concepts[4].id	https://openalex.org/C45374587
concepts[4].level	2
concepts[4].score	0.577837347984314
concepts[4].wikidata	https://www.wikidata.org/wiki/Q12525525
concepts[4].display_name	Computation
concepts[5].id	https://openalex.org/C99844830
concepts[5].level	2
concepts[5].score	0.5651149749755859
concepts[5].wikidata	https://www.wikidata.org/wiki/Q102441924
concepts[5].display_name	Scaling
concepts[6].id	https://openalex.org/C127162648
concepts[6].level	2
concepts[6].score	0.5425522923469543
concepts[6].wikidata	https://www.wikidata.org/wiki/Q16858953
concepts[6].display_name	Channel (broadcasting)
concepts[7].id	https://openalex.org/C2944601119
concepts[7].level	3
concepts[7].score	0.5168288350105286
concepts[7].wikidata	https://www.wikidata.org/wiki/Q43744058
concepts[7].display_name	Residual neural network
concepts[8].id	https://openalex.org/C111335779
concepts[8].level	2
concepts[8].score	0.4891100525856018
concepts[8].wikidata	https://www.wikidata.org/wiki/Q3454686
concepts[8].display_name	Reduction (mathematics)
concepts[9].id	https://openalex.org/C11413529
concepts[9].level	1
concepts[9].score	0.46941882371902466
concepts[9].wikidata	https://www.wikidata.org/wiki/Q8366
concepts[9].display_name	Algorithm
concepts[10].id	https://openalex.org/C154945302
concepts[10].level	1
concepts[10].score	0.3546299338340759
concepts[10].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[10].display_name	Artificial intelligence
concepts[11].id	https://openalex.org/C153180895
concepts[11].level	2
concepts[11].score	0.3435346484184265
concepts[11].wikidata	https://www.wikidata.org/wiki/Q7148389
concepts[11].display_name	Pattern recognition (psychology)
concepts[12].id	https://openalex.org/C31258907
concepts[12].level	1
concepts[12].score	0.1356777846813202
concepts[12].wikidata	https://www.wikidata.org/wiki/Q1301371
concepts[12].display_name	Computer network
concepts[13].id	https://openalex.org/C173608175
concepts[13].level	1
concepts[13].score	0.13493701815605164
concepts[13].wikidata	https://www.wikidata.org/wiki/Q232661
concepts[13].display_name	Parallel computing
concepts[14].id	https://openalex.org/C33923547
concepts[14].level	0
concepts[14].score	0.09864270687103271
concepts[14].wikidata	https://www.wikidata.org/wiki/Q395
concepts[14].display_name	Mathematics
concepts[15].id	https://openalex.org/C86803240
concepts[15].level	0
concepts[15].score	0.0
concepts[15].wikidata	https://www.wikidata.org/wiki/Q420
concepts[15].display_name	Biology
concepts[16].id	https://openalex.org/C6557445
concepts[16].level	1
concepts[16].score	0.0
concepts[16].wikidata	https://www.wikidata.org/wiki/Q173113
concepts[16].display_name	Agronomy
concepts[17].id	https://openalex.org/C2524010
concepts[17].level	1
concepts[17].score	0.0
concepts[17].wikidata	https://www.wikidata.org/wiki/Q8087
concepts[17].display_name	Geometry
keywords[0].id	https://openalex.org/keywords/computer-science
keywords[0].score	0.854586124420166
keywords[0].display_name	Computer science
keywords[1].id	https://openalex.org/keywords/pruning
keywords[1].score	0.8315805196762085
keywords[1].display_name	Pruning
keywords[2].id	https://openalex.org/keywords/flops
keywords[2].score	0.8306771516799927
keywords[2].display_name	FLOPS
keywords[3].id	https://openalex.org/keywords/convolutional-neural-network
keywords[3].score	0.7626126408576965
keywords[3].display_name	Convolutional neural network
keywords[4].id	https://openalex.org/keywords/computation
keywords[4].score	0.577837347984314
keywords[4].display_name	Computation
keywords[5].id	https://openalex.org/keywords/scaling
keywords[5].score	0.5651149749755859
keywords[5].display_name	Scaling
keywords[6].id	https://openalex.org/keywords/channel
keywords[6].score	0.5425522923469543
keywords[6].display_name	Channel (broadcasting)
keywords[7].id	https://openalex.org/keywords/residual-neural-network
keywords[7].score	0.5168288350105286
keywords[7].display_name	Residual neural network
keywords[8].id	https://openalex.org/keywords/reduction
keywords[8].score	0.4891100525856018
keywords[8].display_name	Reduction (mathematics)
keywords[9].id	https://openalex.org/keywords/algorithm
keywords[9].score	0.46941882371902466
keywords[9].display_name	Algorithm
keywords[10].id	https://openalex.org/keywords/artificial-intelligence
keywords[10].score	0.3546299338340759
keywords[10].display_name	Artificial intelligence
keywords[11].id	https://openalex.org/keywords/pattern-recognition
keywords[11].score	0.3435346484184265
keywords[11].display_name	Pattern recognition (psychology)
keywords[12].id	https://openalex.org/keywords/computer-network
keywords[12].score	0.1356777846813202
keywords[12].display_name	Computer network
keywords[13].id	https://openalex.org/keywords/parallel-computing
keywords[13].score	0.13493701815605164
keywords[13].display_name	Parallel computing
keywords[14].id	https://openalex.org/keywords/mathematics
keywords[14].score	0.09864270687103271
keywords[14].display_name	Mathematics
language	en
locations[0].id	doi:10.1587/transinf.2019edl8200
locations[0].is_oa	True
locations[0].source.id	https://openalex.org/S2486202937
locations[0].source.issn	0916-8532, 1745-1361
locations[0].source.type	journal
locations[0].source.is_oa	True
locations[0].source.issn_l	0916-8532
locations[0].source.is_core	True
locations[0].source.is_in_doaj	False
locations[0].source.display_name	IEICE Transactions on Information and Systems
locations[0].source.host_organization	https://openalex.org/P4320800604
locations[0].source.host_organization_name	Institute of Electronics, Information and Communication Engineers
locations[0].source.host_organization_lineage	https://openalex.org/P4320800604
locations[0].source.host_organization_lineage_names	Institute of Electronics, Information and Communication Engineers
locations[0].license
locations[0].pdf_url	https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8200/_pdf
locations[0].version	publishedVersion
locations[0].raw_type	journal-article
locations[0].license_id
locations[0].is_accepted	True
locations[0].is_published	True
locations[0].raw_source_name	IEICE Transactions on Information and Systems
locations[0].landing_page_url	https://doi.org/10.1587/transinf.2019edl8200
indexed_in	crossref
authorships[0].author.id	https://openalex.org/A5101532325
authorships[0].author.orcid	https://orcid.org/0000-0003-3338-3223
authorships[0].author.display_name	Xin Long
authorships[0].countries	CN
authorships[0].affiliations[0].institution_ids	https://openalex.org/I170215575
authorships[0].affiliations[0].raw_affiliation_string	National University of Defense Technology
authorships[0].institutions[0].id	https://openalex.org/I170215575
authorships[0].institutions[0].ror	https://ror.org/05d2yfz11
authorships[0].institutions[0].type	education
authorships[0].institutions[0].lineage	https://openalex.org/I170215575
authorships[0].institutions[0].country_code	CN
authorships[0].institutions[0].display_name	National University of Defense Technology
authorships[0].author_position	first
authorships[0].raw_author_name	Xin LONG
authorships[0].is_corresponding	False
authorships[0].raw_affiliation_strings	National University of Defense Technology
authorships[1].author.id	https://openalex.org/A5030783966
authorships[1].author.orcid	https://orcid.org/0000-0002-4247-9684
authorships[1].author.display_name	Xiangrong Zeng
authorships[1].countries	CN
authorships[1].affiliations[0].institution_ids	https://openalex.org/I170215575
authorships[1].affiliations[0].raw_affiliation_string	National University of Defense Technology
authorships[1].institutions[0].id	https://openalex.org/I170215575
authorships[1].institutions[0].ror	https://ror.org/05d2yfz11
authorships[1].institutions[0].type	education
authorships[1].institutions[0].lineage	https://openalex.org/I170215575
authorships[1].institutions[0].country_code	CN
authorships[1].institutions[0].display_name	National University of Defense Technology
authorships[1].author_position	middle
authorships[1].raw_author_name	Xiangrong ZENG
authorships[1].is_corresponding	False
authorships[1].raw_affiliation_strings	National University of Defense Technology
authorships[2].author.id	https://openalex.org/A5100418568
authorships[2].author.orcid	https://orcid.org/0000-0003-3957-7061
authorships[2].author.display_name	Chen Chen
authorships[2].countries	CN
authorships[2].affiliations[0].institution_ids	https://openalex.org/I170215575
authorships[2].affiliations[0].raw_affiliation_string	National University of Defense Technology
authorships[2].institutions[0].id	https://openalex.org/I170215575
authorships[2].institutions[0].ror	https://ror.org/05d2yfz11
authorships[2].institutions[0].type	education
authorships[2].institutions[0].lineage	https://openalex.org/I170215575
authorships[2].institutions[0].country_code	CN
authorships[2].institutions[0].display_name	National University of Defense Technology
authorships[2].author_position	middle
authorships[2].raw_author_name	Chen CHEN
authorships[2].is_corresponding	False
authorships[2].raw_affiliation_strings	National University of Defense Technology
authorships[3].author.id	https://openalex.org/A5001902162
authorships[3].author.orcid	https://orcid.org/0000-0003-4524-2698
authorships[3].author.display_name	Huaxin Xiao
authorships[3].countries	CN
authorships[3].affiliations[0].institution_ids	https://openalex.org/I170215575
authorships[3].affiliations[0].raw_affiliation_string	National University of Defense Technology
authorships[3].institutions[0].id	https://openalex.org/I170215575
authorships[3].institutions[0].ror	https://ror.org/05d2yfz11
authorships[3].institutions[0].type	education
authorships[3].institutions[0].lineage	https://openalex.org/I170215575
authorships[3].institutions[0].country_code	CN
authorships[3].institutions[0].display_name	National University of Defense Technology
authorships[3].author_position	middle
authorships[3].raw_author_name	Huaxin XIAO
authorships[3].is_corresponding	False
authorships[3].raw_affiliation_strings	National University of Defense Technology
authorships[4].author.id	https://openalex.org/A5100770607
authorships[4].author.orcid	https://orcid.org/0000-0001-6748-0545
authorships[4].author.display_name	Maojun Zhang
authorships[4].countries	CN
authorships[4].affiliations[0].institution_ids	https://openalex.org/I170215575
authorships[4].affiliations[0].raw_affiliation_string	National University of Defense Technology
authorships[4].institutions[0].id	https://openalex.org/I170215575
authorships[4].institutions[0].ror	https://ror.org/05d2yfz11
authorships[4].institutions[0].type	education
authorships[4].institutions[0].lineage	https://openalex.org/I170215575
authorships[4].institutions[0].country_code	CN
authorships[4].institutions[0].display_name	National University of Defense Technology
authorships[4].author_position	last
authorships[4].raw_author_name	Maojun ZHANG
authorships[4].is_corresponding	False
authorships[4].raw_affiliation_strings	National University of Defense Technology
has_content.pdf	True
has_content.grobid_xml	True
is_paratext	False
open_access.is_oa	True
open_access.oa_url	https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8200/_pdf
open_access.oa_status	diamond
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Loss-Driven Channel Pruning of Convolutional Neural Networks
has_fulltext	True
is_retracted	False
updated_date	2025-11-06T03:46:38.306776
primary_topic.id	https://openalex.org/T10036
primary_topic.field.id	https://openalex.org/fields/17
primary_topic.field.display_name	Computer Science
primary_topic.score	1.0
primary_topic.domain.id	https://openalex.org/domains/3
primary_topic.domain.display_name	Physical Sciences
primary_topic.subfield.id	https://openalex.org/subfields/1707
primary_topic.subfield.display_name	Computer Vision and Pattern Recognition
primary_topic.display_name	Advanced Neural Network Applications
related_works	https://openalex.org/W4315697128, https://openalex.org/W3005814217, https://openalex.org/W3134206242, https://openalex.org/W4287272376, https://openalex.org/W3092292339, https://openalex.org/W3213976941, https://openalex.org/W2604192360, https://openalex.org/W2958985755, https://openalex.org/W4360783045, https://openalex.org/W3160421061
cited_by_count	2
counts_by_year[0].year	2021
counts_by_year[0].cited_by_count	1
counts_by_year[1].year	2020
counts_by_year[1].cited_by_count	1
locations_count	1
best_oa_location.id	doi:10.1587/transinf.2019edl8200
best_oa_location.is_oa	True
best_oa_location.source.id	https://openalex.org/S2486202937
best_oa_location.source.issn	0916-8532, 1745-1361
best_oa_location.source.type	journal
best_oa_location.source.is_oa	True
best_oa_location.source.issn_l	0916-8532
best_oa_location.source.is_core	True
best_oa_location.source.is_in_doaj	False
best_oa_location.source.display_name	IEICE Transactions on Information and Systems
best_oa_location.source.host_organization	https://openalex.org/P4320800604
best_oa_location.source.host_organization_name	Institute of Electronics, Information and Communication Engineers
best_oa_location.source.host_organization_lineage	https://openalex.org/P4320800604
best_oa_location.source.host_organization_lineage_names	Institute of Electronics, Information and Communication Engineers
best_oa_location.license
best_oa_location.pdf_url	https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8200/_pdf
best_oa_location.version	publishedVersion
best_oa_location.raw_type	journal-article
best_oa_location.license_id
best_oa_location.is_accepted	True
best_oa_location.is_published	True
best_oa_location.raw_source_name	IEICE Transactions on Information and Systems
best_oa_location.landing_page_url	https://doi.org/10.1587/transinf.2019edl8200
primary_location.id	doi:10.1587/transinf.2019edl8200
primary_location.is_oa	True
primary_location.source.id	https://openalex.org/S2486202937
primary_location.source.issn	0916-8532, 1745-1361
primary_location.source.type	journal
primary_location.source.is_oa	True
primary_location.source.issn_l	0916-8532
primary_location.source.is_core	True
primary_location.source.is_in_doaj	False
primary_location.source.display_name	IEICE Transactions on Information and Systems
primary_location.source.host_organization	https://openalex.org/P4320800604
primary_location.source.host_organization_name	Institute of Electronics, Information and Communication Engineers
primary_location.source.host_organization_lineage	https://openalex.org/P4320800604
primary_location.source.host_organization_lineage_names	Institute of Electronics, Information and Communication Engineers
primary_location.license
primary_location.pdf_url	https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDL8200/_pdf
primary_location.version	publishedVersion
primary_location.raw_type	journal-article
primary_location.license_id
primary_location.is_accepted	True
primary_location.is_published	True
primary_location.raw_source_name	IEICE Transactions on Information and Systems
primary_location.landing_page_url	https://doi.org/10.1587/transinf.2019edl8200
publication_date	2020-04-30
publication_year	2020
referenced_works	https://openalex.org/W2163605009, https://openalex.org/W2102605133, https://openalex.org/W2909577373, https://openalex.org/W2119144962, https://openalex.org/W2754084392, https://openalex.org/W2167215970, https://openalex.org/W1902934009, https://openalex.org/W2300242332, https://openalex.org/W2612445135, https://openalex.org/W2963125010, https://openalex.org/W2556833785, https://openalex.org/W2515385951, https://openalex.org/W2513419314, https://openalex.org/W2940141242, https://openalex.org/W2748428003, https://openalex.org/W2951886768, https://openalex.org/W2405920868
referenced_works_count	17
abstract_inverted_index.a	23, 41, 78
abstract_inverted_index.As	22
abstract_inverted_index.By	73
abstract_inverted_index.In	36, 87
abstract_inverted_index.It	50
abstract_inverted_index.be	131
abstract_inverted_index.by	33, 54, 69
abstract_inverted_index.in	2, 19, 95
abstract_inverted_index.is	26, 114
abstract_inverted_index.no	124
abstract_inverted_index.of	7, 48
abstract_inverted_index.on	16
abstract_inverted_index.to	29, 44, 60, 116, 133
abstract_inverted_index.we	39, 76, 90
abstract_inverted_index.70%	119
abstract_inverted_index.The	0
abstract_inverted_index.and	5, 62, 65, 84, 105, 107, 121
abstract_inverted_index.so,	75
abstract_inverted_index.the	31, 92, 111
abstract_inverted_index.able	115
abstract_inverted_index.cost	4
abstract_inverted_index.less	82
abstract_inverted_index.more	135
abstract_inverted_index.over	118
abstract_inverted_index.this	37
abstract_inverted_index.used	132
abstract_inverted_index.with	81, 98, 123
abstract_inverted_index.CIFAR	96
abstract_inverted_index.CNNs.	49
abstract_inverted_index.FLOPs	85
abstract_inverted_index.could	130
abstract_inverted_index.doing	74
abstract_inverted_index.fixed	70
abstract_inverted_index.loss.	126
abstract_inverted_index.prune	45, 117
abstract_inverted_index.their	14
abstract_inverted_index.there	25
abstract_inverted_index.those	67
abstract_inverted_index.using	55
abstract_inverted_index.(CNNs)	11
abstract_inverted_index.Taylor	56
abstract_inverted_index.method	43, 94, 113
abstract_inverted_index.neural	9
abstract_inverted_index.obtain	77, 134
abstract_inverted_index.paper,	38
abstract_inverted_index.prunes	66
abstract_inverted_index.recent	20
abstract_inverted_index.years.	21
abstract_inverted_index.VGG-19,	103
abstract_inverted_index.certain	34
abstract_inverted_index.compact	79, 136
abstract_inverted_index.devices	18
abstract_inverted_index.hinders	13
abstract_inverted_index.network	80
abstract_inverted_index.popular	100
abstract_inverted_index.propose	40
abstract_inverted_index.pruning	129
abstract_inverted_index.result,	24
abstract_inverted_index.results	109
abstract_inverted_index.scaling	61
abstract_inverted_index.several	99
abstract_inverted_index.storage	6
abstract_inverted_index.channels	47, 53, 68, 120
abstract_inverted_index.datasets	97
abstract_inverted_index.evaluate	91
abstract_inverted_index.factors,	64
abstract_inverted_index.increase	1
abstract_inverted_index.methods.	35
abstract_inverted_index.network.	137
abstract_inverted_index.networks	10, 32
abstract_inverted_index.proposed	93, 112
abstract_inverted_index.section,	89
abstract_inverted_index.severely	12
abstract_inverted_index.shifting	63
abstract_inverted_index.Moreover,	127
abstract_inverted_index.expansion	57
abstract_inverted_index.impending	27
abstract_inverted_index.including	102
abstract_inverted_index.iterative	128
abstract_inverted_index.necessity	28
abstract_inverted_index.networks,	101
abstract_inverted_index.redundant	46
abstract_inverted_index.regarding	59
abstract_inverted_index.technique	58
abstract_inverted_index.accelerate	30
abstract_inverted_index.identifies	51
abstract_inverted_index.parameters	83, 122
abstract_inverted_index.percentile	71
abstract_inverted_index.threshold.	72
abstract_inverted_index.DenseNet-40	104
abstract_inverted_index.ResNet-164,	106
abstract_inverted_index.computation	3
abstract_inverted_index.demonstrate	110
abstract_inverted_index.loss-driven	42
abstract_inverted_index.performance	125
abstract_inverted_index.unimportant	52
abstract_inverted_index.applications	15
abstract_inverted_index.consumption.	86
abstract_inverted_index.experimental	88, 108
abstract_inverted_index.convolutional	8
abstract_inverted_index.limited-resources	17
cited_by_percentile_year.max	94
cited_by_percentile_year.min	89
countries_distinct_count	1
institutions_distinct_count	5
sustainable_development_goals[0].id	https://metadata.un.org/sdg/9
sustainable_development_goals[0].score	0.4300000071525574
sustainable_development_goals[0].display_name	Industry, innovation and infrastructure
citation_normalized_percentile.value	0.49360061
citation_normalized_percentile.is_in_top_1_percent	False
citation_normalized_percentile.is_in_top_10_percent	False