kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
AutoAblation: Automated Parallel Ablation Studies for Deep Learning
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS.ORCID iD: 0000-0001-7236-4637
Logical Clocks AB, Stockholm, Sweden.
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS.
KTH, School of Electrical Engineering and Computer Science (EECS), Computer Science, Software and Computer systems, SCS.ORCID iD: 0000-0002-2748-8929
Show others and affiliations
2021 (English)In: EuroMLSys '21: Proceedings of the 1st Workshop on Machine Learning and Systems, Association for Computing Machinery , 2021, p. 55-61Conference paper, Published paper (Refereed)
Abstract [en]

Ablation studies provide insights into the relative contribution of different architectural and regularization components to machine learning models' performance. In this paper, we introduce AutoAblation, a new framework for the design and parallel execution of ablation experiments. AutoAblation provides a declarative approach to defining ablation experiments on model architectures and training datasets, and enables the parallel execution of ablation trials. This reduces the execution time and allows more comprehensive experiments by exploiting larger amounts of computational resources. We show that AutoAblation can provide near-linear scalability by performing an ablation study on the modules of the Inception-v3 network trained on the TenGeoPSAR dataset.  

Place, publisher, year, edition, pages
Association for Computing Machinery , 2021. p. 55-61
Keywords [en]
Ablation Studies, Deep Learning, Feature Ablation, Model Ablation, Parallel Trial Execution
National Category
Computer Systems
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:kth:diva-294424DOI: 10.1145/3437984.3458834ISI: 000927844400008Scopus ID: 2-s2.0-85106034900OAI: oai:DiVA.org:kth-294424DiVA, id: diva2:1554987
Conference
The 1st Workshop on Machine Learning and Systems (EuroMLSys '21)
Funder
EU, Horizon 2020
Note

QC 20210527

Available from: 2021-05-17 Created: 2021-05-17 Last updated: 2023-09-21Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopushttps://doi.org/10.1145/3437984.3458834

Authority records

Sheikholeslami, SinaWang, TianzePayberah, Amir H.Vlassov, VladimirDowling, Jim

Search in DiVA

By author/editor
Sheikholeslami, SinaWang, TianzePayberah, Amir H.Vlassov, VladimirDowling, Jim
By organisation
Software and Computer systems, SCS
Computer Systems

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 156 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf