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
Energy-Aware Very Fast Decision Tree
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.ORCID iD: 0000-0003-4973-9255
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
Blekinge Institute of Technology, Faculty of Computing, Department of Computer Science.
Show others and affiliations
(English)In: Journal of Data Science and Analytics, ISSN 2364-415XArticle in journal (Refereed) Accepted
Abstract [en]

Recently machine learning researchers are designing algorithms that can run in embedded and mobile devices, which introduces additional constraints compared to traditional algorithm design approaches. One of these constraints is energy consumption, which directly translates to battery capacity for these devices. Streaming algorithms, such as the Very Fast Decision Tree (VFDT), are designed to run in such devices due to their high velocity and low memory requirements. However, they have not been designed with an energy efficiency focus. This paper addresses this challenge by presenting the nmin adaptation method, which reduces the energy consumption of the VFDT algorithm with only minor effects on accuracy. nmin adaptation allows the algorithm to grow faster in those branches where there is more confidence to create a split, and delays the split on the less confident branches. This removes unnecessary computations related to checking for splits but maintains similar levels of accuracy. We have conducted extensive experiments on 29 public datasets, showing that the VFDT with nmin adaptation consumes up to 31% less energy than the original VFDT, and up to 96% less energy than the CVFDT (VFDT adapted for concept drift scenarios), trading off up to 1.7 percent of accuracy.

National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:bth-19150OAI: oai:DiVA.org:bth-19150DiVA, id: diva2:1388159
Funder
Knowledge Foundation, 20140032Available from: 2020-01-23 Created: 2020-01-23 Last updated: 2020-01-28Bibliographically approved
In thesis
1. Energy Efficiency in Machine Learning: Approaches to Sustainable Data Stream Mining
Open this publication in new window or tab >>Energy Efficiency in Machine Learning: Approaches to Sustainable Data Stream Mining
2020 (English)Doctoral thesis, comprehensive summary (Other academic)
Abstract [en]

Energy efficiency in machine learning explores how to build machine learning algorithms and models with low computational and power requirements. Although energy consumption is starting to gain interest in the field of machine learning, still the majority of solutions focus on obtaining the highest predictive accuracy, without a clear focus on sustainability.

This thesis explores green machine learning, which builds on green computing and computer architecture to design sustainable and energy efficient machine learning algorithms. In particular, we investigate how to design machine learning algorithms that automatically learn from streaming data in an energy efficient manner.

We first illustrate how energy can be measured in the context of machine learning, in the form of a literature review and a procedure to create theoretical energy models. We use this knowledge to analyze the energy footprint of Hoeffding trees, presenting an energy model that maps the number of computations and memory accesses to the main functionalities of the algorithm. We also analyze the hardware events correlated to the execution of the algorithm, their functions and their hyper parameters.

The final contribution of the thesis is showcased by two novel extensions of Hoeffding tree algorithms, the Hoeffding tree with nmin adaptation and the Green Accelerated Hoeffding Tree. These solutions are able to reduce their energy consumption by twenty and thirty percent, with minimal effect on accuracy. This is achieved by setting an individual splitting criteria for each branch of the decision tree, spending more energy on the fast growing branches and saving energy on the rest.

This thesis shows the importance of evaluating energy consumption when designing machine learning algorithms, proving that we can design more energy efficient algorithms and still achieve competitive accuracy results.

Place, publisher, year, edition, pages
Karlskrona: Blekinge Tekniska Högskola, 2020. p. 267
Series
Blekinge Institute of Technology Doctoral Dissertation Series, ISSN 1653-2090 ; 2
Keywords
machine learning, energy efficiency, data stream mining, green machine learning, edge computing
National Category
Computer Sciences
Identifiers
urn:nbn:se:bth-18986 (URN)978-91-7295-396-3 (ISBN)
Public defence
2020-01-31, J1650, Blekinge Institute of Technology, Karlskrona, 13:15 (English)
Opponent
Supervisors
Funder
Knowledge Foundation, 20140032
Available from: 2019-12-03 Created: 2019-12-03 Last updated: 2020-02-26Bibliographically approved

Open Access in DiVA

No full text in DiVA

Search in DiVA

By author/editor
García-Martín, Eva
By organisation
Department of Computer Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric score

urn-nbn
Total: 41 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