AdaEvo: Edge-Assisted Continuous and Timely DNN Model Evolution for Mobile Devices
Mobile video applications today have attracted significant attention. Deep learning model (e.g. deep neural network, DNN) compression is widely used to enable on-device inference for facilitating robust and private mobile video applications. The compressed DNN, however, is vulnerable to the agnostic...
Saved in:
Published in | arXiv.org |
---|---|
Main Authors | , , , , , , |
Format | Paper |
Language | English |
Published |
Ithaca
Cornell University Library, arXiv.org
25.10.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Abstract | Mobile video applications today have attracted significant attention. Deep learning model (e.g. deep neural network, DNN) compression is widely used to enable on-device inference for facilitating robust and private mobile video applications. The compressed DNN, however, is vulnerable to the agnostic data drift of the live video captured from the dynamically changing mobile scenarios. To combat the data drift, mobile ends rely on edge servers to continuously evolve and re-compress the DNN with freshly collected data. We design a framework, AdaEvo, that efficiently supports the resource-limited edge server handling mobile DNN evolution tasks from multiple mobile ends. The key goal of AdaEvo is to maximize the average quality of experience (QoE), e.g. the proportion of high-quality DNN service time to the entire life cycle, for all mobile ends. Specifically, it estimates the DNN accuracy drops at the mobile end without labels and performs a dedicated video frame sampling strategy to control the size of retraining data. In addition, it balances the limited computing and memory resources on the edge server and the competition between asynchronous tasks initiated by different mobile users. With an extensive evaluation of real-world videos from mobile scenarios and across four diverse mobile tasks, experimental results show that AdaEvo enables up to 34% accuracy improvement and 32% average QoE improvement. |
---|---|
AbstractList | Mobile video applications today have attracted significant attention. Deep learning model (e.g. deep neural network, DNN) compression is widely used to enable on-device inference for facilitating robust and private mobile video applications. The compressed DNN, however, is vulnerable to the agnostic data drift of the live video captured from the dynamically changing mobile scenarios. To combat the data drift, mobile ends rely on edge servers to continuously evolve and re-compress the DNN with freshly collected data. We design a framework, AdaEvo, that efficiently supports the resource-limited edge server handling mobile DNN evolution tasks from multiple mobile ends. The key goal of AdaEvo is to maximize the average quality of experience (QoE), e.g. the proportion of high-quality DNN service time to the entire life cycle, for all mobile ends. Specifically, it estimates the DNN accuracy drops at the mobile end without labels and performs a dedicated video frame sampling strategy to control the size of retraining data. In addition, it balances the limited computing and memory resources on the edge server and the competition between asynchronous tasks initiated by different mobile users. With an extensive evaluation of real-world videos from mobile scenarios and across four diverse mobile tasks, experimental results show that AdaEvo enables up to 34% accuracy improvement and 32% average QoE improvement. |
Author | Guo, Bin Yu, Haoyi Liu, Sicong Xie, Yaxiong Yu, Zhiwen Liu, Yunxin Wang, Lehao |
Author_xml | – sequence: 1 givenname: Lehao surname: Wang fullname: Wang, Lehao – sequence: 2 givenname: Zhiwen surname: Yu fullname: Yu, Zhiwen – sequence: 3 givenname: Haoyi surname: Yu fullname: Yu, Haoyi – sequence: 4 givenname: Sicong surname: Liu fullname: Liu, Sicong – sequence: 5 givenname: Yaxiong surname: Xie fullname: Xie, Yaxiong – sequence: 6 givenname: Bin surname: Guo fullname: Guo, Bin – sequence: 7 givenname: Yunxin surname: Liu fullname: Liu, Yunxin |
BookMark | eNqNi8EKgkAURYcoyMp_eNBasBlNbRdmtMlFtA9rXjExzSufE_T3uegDWl0459yJGDpyOBCBVGoR5YmUYxEy3-M4lstMpqkKxGGtm-pNK6j0DaM1s-EONZTkOuM8eYbGaTiaB9oPbOoa9qTRQn-xvjPk4Eptz87GImzwbS7IMzG6NpYx_O1UzLfVsdxFz5ZeHrk73cm3rlcnmS-LrMiLPFH_VV-3kUCD |
ContentType | Paper |
Copyright | 2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
Copyright_xml | – notice: 2023. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
DBID | 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO HCIFZ L6V M7S PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
DatabaseName | ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni) ProQuest Central ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One Community College ProQuest Central SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Engineering Collection Engineering Database Publicly Available Content Database ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection |
DatabaseTitle | Publicly Available Content Database Engineering Database Technology Collection ProQuest Central Essentials ProQuest One Academic Eastern Edition ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Technology Collection ProQuest SciTech Collection ProQuest Central China ProQuest Central ProQuest Engineering Collection ProQuest One Academic UKI Edition ProQuest Central Korea Materials Science & Engineering Collection ProQuest One Academic Engineering Collection |
DatabaseTitleList | Publicly Available Content Database |
Database_xml | – sequence: 1 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
DeliveryMethod | fulltext_linktorsrc |
Discipline | Physics |
EISSN | 2331-8422 |
Genre | Working Paper/Pre-Print |
GroupedDBID | 8FE 8FG ABJCF ABUWG AFKRA ALMA_UNASSIGNED_HOLDINGS AZQEC BENPR BGLVJ CCPQU DWQXO FRJ HCIFZ L6V M7S M~E PIMPY PQEST PQQKQ PQUKI PRINS PTHSS |
ID | FETCH-proquest_journals_28697989843 |
IEDL.DBID | 8FG |
IngestDate | Thu Oct 10 17:51:38 EDT 2024 |
IsOpenAccess | true |
IsPeerReviewed | false |
IsScholarly | false |
Language | English |
LinkModel | DirectLink |
MergedId | FETCHMERGED-proquest_journals_28697989843 |
OpenAccessLink | https://www.proquest.com/docview/2869798984?pq-origsite=%requestingapplication% |
PQID | 2869798984 |
PQPubID | 2050157 |
ParticipantIDs | proquest_journals_2869798984 |
PublicationCentury | 2000 |
PublicationDate | 20231025 |
PublicationDateYYYYMMDD | 2023-10-25 |
PublicationDate_xml | – month: 10 year: 2023 text: 20231025 day: 25 |
PublicationDecade | 2020 |
PublicationPlace | Ithaca |
PublicationPlace_xml | – name: Ithaca |
PublicationTitle | arXiv.org |
PublicationYear | 2023 |
Publisher | Cornell University Library, arXiv.org |
Publisher_xml | – name: Cornell University Library, arXiv.org |
SSID | ssj0002672553 |
Score | 3.5088544 |
SecondaryResourceType | preprint |
Snippet | Mobile video applications today have attracted significant attention. Deep learning model (e.g. deep neural network, DNN) compression is widely used to enable... |
SourceID | proquest |
SourceType | Aggregation Database |
SubjectTerms | Accuracy Artificial neural networks Data collection Drift Edge computing Evolution Machine learning Mobile computing Servers Streaming media Video compression |
Title | AdaEvo: Edge-Assisted Continuous and Timely DNN Model Evolution for Mobile Devices |
URI | https://www.proquest.com/docview/2869798984 |
hasFullText | 1 |
inHoldings | 1 |
isFullTextHit | |
isPrint | |
link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3NS8MwFH_oiuDNT_yYI6DXYtcmaeNF1LUOYWUMhd1G0mQijG2u28CLf7vvlU4Pwo5JICSPvI_fS15-ADdj4ZQTRvjCIVblKih8nRjnK664Q4dSKEXVyL1cdt_4y1AM64RbWT-r3NjEylDbWUE58tswkSomskN-P__0iTWKbldrCo1d8Nr0Ex5VimfPvzmWUMYYMUf_zGzlO7ID8Pp67haHsOOmR7BXPbksymMYPFidrmd3LLXvzkcxkcAto--iPqYrBOQMQT6jEo3JF-vkOSPasglL1_VhYRhuYp9BtWYdVyn8CVxn6etT198sZFQflXL0t7HoFBqI-d0ZMG7b2iY6ia1BN8PHSZRIaRC-SR1oF4hzaG6b6WL78CXsE2s6meBQNKGxXKzcFfrWpWlVAmyB95jm_QG2et_pD6abg_k |
link.rule.ids | 786,790,12792,21416,33406,33777,43633,43838 |
linkProvider | ProQuest |
linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3fS8MwED60RfTNn_hjakBfg3VL0sYXUddRdStjTNhbSZpsCGOb6zbwv_dSOn0Q9ppASI7cd_kuyX0At0NupeWaU26RqzIZ5FRF2lLJJLMYUHIp3W_kTiqSD_Y24IMq4VZUzyrXmFgCtZnmLkd-V4-EDJ3YIXucfVGnGuVuVysJjW3wXcnNyAP_OU67vd8sS12EeGZu_APaMnq09sHvqpmdH8CWnRzCTvnoMi-OoPdkVLyaPpDYjCxFQzmTG-IKRn1OlkjJCdJ84j5pjL9JM02JEy4bk3hVbReCB05s0-jYpGlLlz-Gm1bcf0noeiJZtVmK7G9pjRPwkPXbUyDM3CsTqSg0GgMNG-LqhNBI4IQKlA34GdQ2jXS-ufsadpN-p521X9P3C9hzGuoOkOu8Bt5ivrSXGGkX-qoy5w_7YYWF |
openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=AdaEvo%3A+Edge-Assisted+Continuous+and+Timely+DNN+Model+Evolution+for+Mobile+Devices&rft.jtitle=arXiv.org&rft.au=Wang%2C+Lehao&rft.au=Yu%2C+Zhiwen&rft.au=Yu%2C+Haoyi&rft.au=Liu%2C+Sicong&rft.date=2023-10-25&rft.pub=Cornell+University+Library%2C+arXiv.org&rft.eissn=2331-8422 |