Unsupervised extremely randomized trees

Kevin Dalleau 1 Miguel Couceiro 1 Malika Smaïl-Tabbone 2
1 ORPAILLEUR - Knowledge representation, reasonning
Inria Nancy - Grand Est, LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
2 CAPSID - Computational Algorithms for Protein Structures and Interactions
Inria Nancy - Grand Est, LORIA - AIS - Department of Complex Systems, Artificial Intelligence & Robotics
Abstract : In this paper we present a method to compute dissimilarities on unlabeled data, based on extremely randomized trees. This method, Unsupervised Extremely Randomized Trees, is used jointly with a novel randomized labeling scheme we describe here, and that we call AddCl3. Unlike existing methods such as AddCl1 and AddCl2, no synthetic instances are generated, thus avoiding an increase in the size of the dataset. The empirical study of this method shows that Unsupervised Extremely Randomized Trees with AddCl3 provides competitive results regarding the quality of resulting clusterings, while clearly outperforming previous similar methods in terms of running time.
Document type :
Conference papers
Complete list of metadatas

Cited literature [20 references]  Display  Hide  Download

https://hal.inria.fr/hal-01667317
Contributor : Kevin Dalleau <>
Submitted on : Tuesday, October 16, 2018 - 5:47:35 PM
Last modification on : Thursday, February 7, 2019 - 4:53:32 PM

File

unsupervised-extremely-randomi...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01667317, version 2

Citation

Kevin Dalleau, Miguel Couceiro, Malika Smaïl-Tabbone. Unsupervised extremely randomized trees. PAKDD 2018 - The 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining, May 2018, Melbourne, Australia. ⟨hal-01667317v2⟩

Share

Metrics

Record views

155

Files downloads

227