The Impact of Latency on Online Classification Learning with Concept Drift

Gary R. Marrs, RJ Hickey, Michaela Black

Research output: Chapter in Book/Report/Conference proceedingConference contribution

22 Citations (Scopus)

Abstract

Online classification learners operating under concept drift can be subject to latency in examples arriving at the training base. A discussion of latency and the related notion of example filtering leads to the development of an example life cycle for online learning (OLLC). Latency in a data stream is modelled in a new Example Life-cycle Integrated Simulation Environment (ELISE). In a series of experiments, the online learner algorithm CD3 is evaluated under several drift and latency scenarios. Results show that systems subject to large random latencies can, when drift occurs, suffer substantial deterioration in classification rate with slow recovery.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages459-469
Number of pages10
Volume6291/2
DOIs
Publication statusPublished - 2010
EventThe fourth International Conference on Knowledge Science, Engineering and Management (KSEM`2010) - Belfast, Northern Ireland
Duration: 1 Jan 2010 → …

Conference

ConferenceThe fourth International Conference on Knowledge Science, Engineering and Management (KSEM`2010)
Period1/01/10 → …

Fingerprint

Life cycle
Deterioration
Recovery
Experiments

Keywords

  • Online Learning
  • Classification
  • Concept Drift
  • Data stream
  • Example life-cycle
  • Latency
  • ELISE
  • CD3

Cite this

Marrs, G. R., Hickey, RJ., & Black, M. (2010). The Impact of Latency on Online Classification Learning with Concept Drift. In Unknown Host Publication (Vol. 6291/2, pp. 459-469) https://doi.org/10.1007/978-3-642-15280-1_42
Marrs, Gary R. ; Hickey, RJ ; Black, Michaela. / The Impact of Latency on Online Classification Learning with Concept Drift. Unknown Host Publication. Vol. 6291/2 2010. pp. 459-469
@inproceedings{157fd88eb3e54f78b43e6066423bd8b9,
title = "The Impact of Latency on Online Classification Learning with Concept Drift",
abstract = "Online classification learners operating under concept drift can be subject to latency in examples arriving at the training base. A discussion of latency and the related notion of example filtering leads to the development of an example life cycle for online learning (OLLC). Latency in a data stream is modelled in a new Example Life-cycle Integrated Simulation Environment (ELISE). In a series of experiments, the online learner algorithm CD3 is evaluated under several drift and latency scenarios. Results show that systems subject to large random latencies can, when drift occurs, suffer substantial deterioration in classification rate with slow recovery.",
keywords = "Online Learning, Classification, Concept Drift, Data stream, Example life-cycle, Latency, ELISE, CD3",
author = "Marrs, {Gary R.} and RJ Hickey and Michaela Black",
year = "2010",
doi = "10.1007/978-3-642-15280-1_42",
language = "English",
volume = "6291/2",
pages = "459--469",
booktitle = "Unknown Host Publication",

}

Marrs, GR, Hickey, RJ & Black, M 2010, The Impact of Latency on Online Classification Learning with Concept Drift. in Unknown Host Publication. vol. 6291/2, pp. 459-469, The fourth International Conference on Knowledge Science, Engineering and Management (KSEM`2010), 1/01/10. https://doi.org/10.1007/978-3-642-15280-1_42

The Impact of Latency on Online Classification Learning with Concept Drift. / Marrs, Gary R.; Hickey, RJ; Black, Michaela.

Unknown Host Publication. Vol. 6291/2 2010. p. 459-469.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - The Impact of Latency on Online Classification Learning with Concept Drift

AU - Marrs, Gary R.

AU - Hickey, RJ

AU - Black, Michaela

PY - 2010

Y1 - 2010

N2 - Online classification learners operating under concept drift can be subject to latency in examples arriving at the training base. A discussion of latency and the related notion of example filtering leads to the development of an example life cycle for online learning (OLLC). Latency in a data stream is modelled in a new Example Life-cycle Integrated Simulation Environment (ELISE). In a series of experiments, the online learner algorithm CD3 is evaluated under several drift and latency scenarios. Results show that systems subject to large random latencies can, when drift occurs, suffer substantial deterioration in classification rate with slow recovery.

AB - Online classification learners operating under concept drift can be subject to latency in examples arriving at the training base. A discussion of latency and the related notion of example filtering leads to the development of an example life cycle for online learning (OLLC). Latency in a data stream is modelled in a new Example Life-cycle Integrated Simulation Environment (ELISE). In a series of experiments, the online learner algorithm CD3 is evaluated under several drift and latency scenarios. Results show that systems subject to large random latencies can, when drift occurs, suffer substantial deterioration in classification rate with slow recovery.

KW - Online Learning

KW - Classification

KW - Concept Drift

KW - Data stream

KW - Example life-cycle

KW - Latency

KW - ELISE

KW - CD3

U2 - 10.1007/978-3-642-15280-1_42

DO - 10.1007/978-3-642-15280-1_42

M3 - Conference contribution

VL - 6291/2

SP - 459

EP - 469

BT - Unknown Host Publication

ER -