Growing Efficient Accurate and Robust Neural Networks on the Edge Article Swipe

PDF

Vignesh Sundaresha , Naresh R. Shanbhag ·

YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2410.07691

The ubiquitous deployment of deep learning systems on resource-constrained Edge devices is hindered by their high computational complexity coupled with their fragility to out-of-distribution (OOD) data, especially to naturally occurring common corruptions. Current solutions rely on the Cloud to train and compress models before deploying to the Edge. This incurs high energy and latency costs in transmitting locally acquired field data to the Cloud while also raising privacy concerns. We propose GEARnn (Growing Efficient, Accurate, and Robust neural networks) to grow and train robust networks in-situ, i.e., completely on the Edge device. Starting with a low-complexity initial backbone network, GEARnn employs One-Shot Growth (OSG) to grow a network satisfying the memory constraints of the Edge device using clean data, and robustifies the network using Efficient Robust Augmentation (ERA) to obtain the final network. We demonstrate results on a NVIDIA Jetson Xavier NX, and analyze the trade-offs between accuracy, robustness, model size, energy consumption, and training time. Our results demonstrate the construction of efficient, accurate, and robust networks entirely on an Edge device.

Related Topics

Enhanced Data Rates For Gsm Evolution

Computer Science

Deep Learning

Artificial Intelligence

Concepts

Enhanced Data Rates for GSM Evolution Artificial neural network Computer science Deep neural networks Artificial intelligence

Metadata

Type: preprint
Language: en
Landing Page: http://arxiv.org/abs/2410.07691
PDF: https://arxiv.org/pdf/2410.07691
OA Status: green
Related Works: 10
OpenAlex ID: https://openalex.org/W4403364639

All OpenAlex metadata

Raw OpenAlex JSON

OpenAlex ID: https://openalex.org/W4403364639

Canonical identifier for this work in OpenAlex
DOI: https://doi.org/10.48550/arxiv.2410.07691

Digital Object Identifier
Title: Growing Efficient Accurate and Robust Neural Networks on the Edge

Work title
Type: preprint

OpenAlex work type
Language: en

Primary language
Publication year: 2024

Year of publication
Publication date: 2024-10-10

Full publication date if available
Authors: Vignesh Sundaresha, Naresh R. Shanbhag

List of authors in order
Landing page: https://arxiv.org/abs/2410.07691

Publisher landing page
PDF URL: https://arxiv.org/pdf/2410.07691

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/2410.07691

Direct OA link when available
Concepts: Enhanced Data Rates for GSM Evolution, Artificial neural network, Computer science, Deep neural networks, Artificial intelligence

Top concepts (fields/topics) attached by OpenAlex
Cited by: 0

Total citation count in OpenAlex
Related works (count): 10

Other works algorithmically related by OpenAlex

Full payload

id	https://openalex.org/W4403364639
doi	https://doi.org/10.48550/arxiv.2410.07691
ids.doi	https://doi.org/10.48550/arxiv.2410.07691
ids.openalex	https://openalex.org/W4403364639
fwci
type	preprint
title	Growing Efficient Accurate and Robust Neural Networks on the Edge
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	0.9377999901771545
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/C162307627
concepts[0].level	2
concepts[0].score	0.6614760160446167
concepts[0].wikidata	https://www.wikidata.org/wiki/Q204833
concepts[0].display_name	Enhanced Data Rates for GSM Evolution
concepts[1].id	https://openalex.org/C50644808
concepts[1].level	2
concepts[1].score	0.5695120096206665
concepts[1].wikidata	https://www.wikidata.org/wiki/Q192776
concepts[1].display_name	Artificial neural network
concepts[2].id	https://openalex.org/C41008148
concepts[2].level	0
concepts[2].score	0.5239858031272888
concepts[2].wikidata	https://www.wikidata.org/wiki/Q21198
concepts[2].display_name	Computer science
concepts[3].id	https://openalex.org/C2984842247
concepts[3].level	3
concepts[3].score	0.43637973070144653
concepts[3].wikidata	https://www.wikidata.org/wiki/Q197536
concepts[3].display_name	Deep neural networks
concepts[4].id	https://openalex.org/C154945302
concepts[4].level	1
concepts[4].score	0.42961210012435913
concepts[4].wikidata	https://www.wikidata.org/wiki/Q11660
concepts[4].display_name	Artificial intelligence
keywords[0].id	https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution
keywords[0].score	0.6614760160446167
keywords[0].display_name	Enhanced Data Rates for GSM Evolution
keywords[1].id	https://openalex.org/keywords/artificial-neural-network
keywords[1].score	0.5695120096206665
keywords[1].display_name	Artificial neural network
keywords[2].id	https://openalex.org/keywords/computer-science
keywords[2].score	0.5239858031272888
keywords[2].display_name	Computer science
keywords[3].id	https://openalex.org/keywords/deep-neural-networks
keywords[3].score	0.43637973070144653
keywords[3].display_name	Deep neural networks
keywords[4].id	https://openalex.org/keywords/artificial-intelligence
keywords[4].score	0.42961210012435913
keywords[4].display_name	Artificial intelligence
language	en
locations[0].id	pmh:oai:arXiv.org:2410.07691
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/2410.07691
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/2410.07691
locations[1].id	doi:10.48550/arxiv.2410.07691
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.2410.07691
indexed_in	arxiv, datacite
authorships[0].author.id	https://openalex.org/A5045308819
authorships[0].author.orcid
authorships[0].author.display_name	Vignesh Sundaresha
authorships[0].author_position	first
authorships[0].raw_author_name	Sundaresha, Vignesh
authorships[0].is_corresponding	False
authorships[1].author.id	https://openalex.org/A5057014407
authorships[1].author.orcid	https://orcid.org/0000-0002-4323-9164
authorships[1].author.display_name	Naresh R. Shanbhag
authorships[1].author_position	last
authorships[1].raw_author_name	Shanbhag, Naresh
authorships[1].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/2410.07691
open_access.oa_status	green
open_access.any_repository_has_fulltext	False
created_date	2025-10-10T00:00:00
display_name	Growing Efficient Accurate and Robust Neural Networks on the Edge
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	0.9377999901771545
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/W2748952813, https://openalex.org/W2390279801, https://openalex.org/W2358668433, https://openalex.org/W4396701345, https://openalex.org/W2376932109, https://openalex.org/W2001405890, https://openalex.org/W4396696052, https://openalex.org/W4402327032, https://openalex.org/W2382290278
cited_by_count	0
locations_count	2
best_oa_location.id	pmh:oai:arXiv.org:2410.07691
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/2410.07691
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/2410.07691
primary_location.id	pmh:oai:arXiv.org:2410.07691
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/2410.07691
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/2410.07691
publication_date	2024-10-10
publication_year	2024
referenced_works_count	0
abstract_inverted_index.a	94, 106, 137
abstract_inverted_index.We	69, 133
abstract_inverted_index.an	169
abstract_inverted_index.by	13
abstract_inverted_index.in	55
abstract_inverted_index.is	11
abstract_inverted_index.of	3, 112, 161
abstract_inverted_index.on	7, 35, 88, 136, 168
abstract_inverted_index.to	22, 27, 38, 45, 61, 79, 104, 128
abstract_inverted_index.NX,	141
abstract_inverted_index.Our	156
abstract_inverted_index.The	0
abstract_inverted_index.and	40, 52, 75, 81, 119, 142, 153, 164
abstract_inverted_index.the	36, 46, 62, 89, 109, 113, 121, 130, 144, 159
abstract_inverted_index.Edge	9, 90, 114, 170
abstract_inverted_index.This	48
abstract_inverted_index.also	65
abstract_inverted_index.data	60
abstract_inverted_index.deep	4
abstract_inverted_index.grow	80, 105
abstract_inverted_index.high	15, 50
abstract_inverted_index.rely	34
abstract_inverted_index.with	19, 93
abstract_inverted_index.(ERA)	127
abstract_inverted_index.(OOD)	24
abstract_inverted_index.(OSG)	103
abstract_inverted_index.Cloud	37, 63
abstract_inverted_index.Edge.	47
abstract_inverted_index.clean	117
abstract_inverted_index.costs	54
abstract_inverted_index.data,	25, 118
abstract_inverted_index.field	59
abstract_inverted_index.final	131
abstract_inverted_index.i.e.,	86
abstract_inverted_index.model	149
abstract_inverted_index.size,	150
abstract_inverted_index.their	14, 20
abstract_inverted_index.time.	155
abstract_inverted_index.train	39, 82
abstract_inverted_index.using	116, 123
abstract_inverted_index.while	64
abstract_inverted_index.GEARnn	71, 99
abstract_inverted_index.Growth	102
abstract_inverted_index.Jetson	139
abstract_inverted_index.NVIDIA	138
abstract_inverted_index.Robust	76, 125
abstract_inverted_index.Xavier	140
abstract_inverted_index.before	43
abstract_inverted_index.common	30
abstract_inverted_index.device	115
abstract_inverted_index.energy	51, 151
abstract_inverted_index.incurs	49
abstract_inverted_index.memory	110
abstract_inverted_index.models	42
abstract_inverted_index.neural	77
abstract_inverted_index.obtain	129
abstract_inverted_index.robust	83, 165
abstract_inverted_index.Current	32
abstract_inverted_index.analyze	143
abstract_inverted_index.between	146
abstract_inverted_index.coupled	18
abstract_inverted_index.device.	91, 171
abstract_inverted_index.devices	10
abstract_inverted_index.employs	100
abstract_inverted_index.initial	96
abstract_inverted_index.latency	53
abstract_inverted_index.locally	57
abstract_inverted_index.network	107, 122
abstract_inverted_index.privacy	67
abstract_inverted_index.propose	70
abstract_inverted_index.raising	66
abstract_inverted_index.results	135, 157
abstract_inverted_index.systems	6
abstract_inverted_index.(Growing	72
abstract_inverted_index.One-Shot	101
abstract_inverted_index.Starting	92
abstract_inverted_index.acquired	58
abstract_inverted_index.backbone	97
abstract_inverted_index.compress	41
abstract_inverted_index.entirely	167
abstract_inverted_index.hindered	12
abstract_inverted_index.in-situ,	85
abstract_inverted_index.learning	5
abstract_inverted_index.network,	98
abstract_inverted_index.network.	132
abstract_inverted_index.networks	84, 166
abstract_inverted_index.training	154
abstract_inverted_index.Accurate,	74
abstract_inverted_index.Efficient	124
abstract_inverted_index.accuracy,	147
abstract_inverted_index.accurate,	163
abstract_inverted_index.concerns.	68
abstract_inverted_index.deploying	44
abstract_inverted_index.fragility	21
abstract_inverted_index.naturally	28
abstract_inverted_index.networks)	78
abstract_inverted_index.occurring	29
abstract_inverted_index.solutions	33
abstract_inverted_index.Efficient,	73
abstract_inverted_index.completely	87
abstract_inverted_index.complexity	17
abstract_inverted_index.deployment	2
abstract_inverted_index.efficient,	162
abstract_inverted_index.especially	26
abstract_inverted_index.satisfying	108
abstract_inverted_index.trade-offs	145
abstract_inverted_index.ubiquitous	1
abstract_inverted_index.constraints	111
abstract_inverted_index.demonstrate	134, 158
abstract_inverted_index.robustifies	120
abstract_inverted_index.robustness,	148
abstract_inverted_index.Augmentation	126
abstract_inverted_index.construction	160
abstract_inverted_index.consumption,	152
abstract_inverted_index.corruptions.	31
abstract_inverted_index.transmitting	56
abstract_inverted_index.computational	16
abstract_inverted_index.low-complexity	95
abstract_inverted_index.out-of-distribution	23
abstract_inverted_index.resource-constrained	8
cited_by_percentile_year
countries_distinct_count	0
institutions_distinct_count	2
citation_normalized_percentile