Comparisons between heuristics based on correlativity and efficiency for landmarker generation

Daren Ler*, Irena Koprinska, Sanjay Chawla

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

Recently, we proposed a new meta-learning approach based on landmarking. This approach, which utilises a new set of criteria for selecting landmarkers, generates a set of landmarkers that are each functions over the performance over subsets of the candidate algorithms being landmarked. In this paper, we experiment with three heuristics based on correlativity and efficiency. With each heuristic, the landmarkers generated using linear regression are able to estimate accuracy well, even when only utilising a small fraction of the given algorithms. The results also show that the heuristic in which efficiencies are estimated via 1-nearest neighbour outperformed the other heuristics.

Original languageEnglish
Title of host publicationProceedings - HIS'04
Subtitle of host publication4th International Conference on Hybrid Intelligent Systems
EditorsM. Ishikawa, S. Hashimoto, M. Paprzycki, E. Barakova, K. Yoshida, M. Koppen, D.M. Corne, A. Abraham
Pages32-37
Number of pages6
Publication statusPublished - 2005
Externally publishedYes
EventProceedings - HIS'04: 4th International Conference on Hybrid Intelligent Systems - Kitakyushu, Japan
Duration: 5 Dec 20048 Dec 2004

Publication series

NameProceedings - HIS'04: 4th International Conference on Hybrid Intelligent Systems

Conference

ConferenceProceedings - HIS'04: 4th International Conference on Hybrid Intelligent Systems
Country/TerritoryJapan
CityKitakyushu
Period5/12/048/12/04

Fingerprint

Dive into the research topics of 'Comparisons between heuristics based on correlativity and efficiency for landmarker generation'. Together they form a unique fingerprint.

Cite this