Fast on-line kernel learning for trees

Fabio Aiolli, Giovanni Martino, Alessandro Sperduti, Alessandro Moschitti

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

10 Citations (Scopus)

Abstract

Kernel methods have been shown to be very effective for applications requiring the modeling of structured objects. However kernels for structures usually are too computational demanding to be applied to complex learning algorithms, e.g. Support Vector Machines. Consequently, in order to apply kernels to large amount of structured data, we need fast on-line algorithms along with an efficiency optimization of kernel-based computations. In this paper, we optimize this computation by representing set of trees by minimal Direct Acyclic Graphs (DAGs) allowing us i) to reduce the storage requirements and U) to speed up the evaluation on large number of trees as it can be done 'one-shot' by computing kernels over DAGs. The experiments on predicate argument subtrees from PropBank data show that substantial computational savings can be obtained for the perceptron algorithm.

Original languageEnglish
Title of host publicationProceedings - IEEE International Conference on Data Mining, ICDM
Pages787-791
Number of pages5
DOIs
Publication statusPublished - 1 Dec 2006
Externally publishedYes
Event6th International Conference on Data Mining, ICDM 2006 - Hong Kong, China
Duration: 18 Dec 200622 Dec 2006

Other

Other6th International Conference on Data Mining, ICDM 2006
CountryChina
CityHong Kong
Period18/12/0622/12/06

Fingerprint

Learning algorithms
Support vector machines
Neural networks
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Aiolli, F., Martino, G., Sperduti, A., & Moschitti, A. (2006). Fast on-line kernel learning for trees. In Proceedings - IEEE International Conference on Data Mining, ICDM (pp. 787-791). [4053103] https://doi.org/10.1109/ICDM.2006.69

Fast on-line kernel learning for trees. / Aiolli, Fabio; Martino, Giovanni; Sperduti, Alessandro; Moschitti, Alessandro.

Proceedings - IEEE International Conference on Data Mining, ICDM. 2006. p. 787-791 4053103.

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

Aiolli, F, Martino, G, Sperduti, A & Moschitti, A 2006, Fast on-line kernel learning for trees. in Proceedings - IEEE International Conference on Data Mining, ICDM., 4053103, pp. 787-791, 6th International Conference on Data Mining, ICDM 2006, Hong Kong, China, 18/12/06. https://doi.org/10.1109/ICDM.2006.69
Aiolli F, Martino G, Sperduti A, Moschitti A. Fast on-line kernel learning for trees. In Proceedings - IEEE International Conference on Data Mining, ICDM. 2006. p. 787-791. 4053103 https://doi.org/10.1109/ICDM.2006.69
Aiolli, Fabio ; Martino, Giovanni ; Sperduti, Alessandro ; Moschitti, Alessandro. / Fast on-line kernel learning for trees. Proceedings - IEEE International Conference on Data Mining, ICDM. 2006. pp. 787-791
@inproceedings{22634534e3724966aee91835f280680f,
title = "Fast on-line kernel learning for trees",
abstract = "Kernel methods have been shown to be very effective for applications requiring the modeling of structured objects. However kernels for structures usually are too computational demanding to be applied to complex learning algorithms, e.g. Support Vector Machines. Consequently, in order to apply kernels to large amount of structured data, we need fast on-line algorithms along with an efficiency optimization of kernel-based computations. In this paper, we optimize this computation by representing set of trees by minimal Direct Acyclic Graphs (DAGs) allowing us i) to reduce the storage requirements and U) to speed up the evaluation on large number of trees as it can be done 'one-shot' by computing kernels over DAGs. The experiments on predicate argument subtrees from PropBank data show that substantial computational savings can be obtained for the perceptron algorithm.",
author = "Fabio Aiolli and Giovanni Martino and Alessandro Sperduti and Alessandro Moschitti",
year = "2006",
month = "12",
day = "1",
doi = "10.1109/ICDM.2006.69",
language = "English",
isbn = "0769527019",
pages = "787--791",
booktitle = "Proceedings - IEEE International Conference on Data Mining, ICDM",

}

TY - GEN

T1 - Fast on-line kernel learning for trees

AU - Aiolli, Fabio

AU - Martino, Giovanni

AU - Sperduti, Alessandro

AU - Moschitti, Alessandro

PY - 2006/12/1

Y1 - 2006/12/1

N2 - Kernel methods have been shown to be very effective for applications requiring the modeling of structured objects. However kernels for structures usually are too computational demanding to be applied to complex learning algorithms, e.g. Support Vector Machines. Consequently, in order to apply kernels to large amount of structured data, we need fast on-line algorithms along with an efficiency optimization of kernel-based computations. In this paper, we optimize this computation by representing set of trees by minimal Direct Acyclic Graphs (DAGs) allowing us i) to reduce the storage requirements and U) to speed up the evaluation on large number of trees as it can be done 'one-shot' by computing kernels over DAGs. The experiments on predicate argument subtrees from PropBank data show that substantial computational savings can be obtained for the perceptron algorithm.

AB - Kernel methods have been shown to be very effective for applications requiring the modeling of structured objects. However kernels for structures usually are too computational demanding to be applied to complex learning algorithms, e.g. Support Vector Machines. Consequently, in order to apply kernels to large amount of structured data, we need fast on-line algorithms along with an efficiency optimization of kernel-based computations. In this paper, we optimize this computation by representing set of trees by minimal Direct Acyclic Graphs (DAGs) allowing us i) to reduce the storage requirements and U) to speed up the evaluation on large number of trees as it can be done 'one-shot' by computing kernels over DAGs. The experiments on predicate argument subtrees from PropBank data show that substantial computational savings can be obtained for the perceptron algorithm.

UR - http://www.scopus.com/inward/record.url?scp=84864547838&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864547838&partnerID=8YFLogxK

U2 - 10.1109/ICDM.2006.69

DO - 10.1109/ICDM.2006.69

M3 - Conference contribution

SN - 0769527019

SN - 9780769527017

SP - 787

EP - 791

BT - Proceedings - IEEE International Conference on Data Mining, ICDM

ER -