On the Combination of Argumentation Solvers into Parallel Portfolios

Mauro Vallati, Federico Cerutti, Massimiliano Giacomin

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

1 Citation (Scopus)

Abstract

In the light of the increasing interest in efficient algorithms for solving abstract argumentation problems and the pervasive availability of multicore machines, a natural research issue is to combine existing argumentation solvers into parallel portfolios. In this work, we introduce six methodologies for the automatic configuration of parallel portfolios of argumentation solvers for enumerating the preferred extensions of a given framework. In particular, four methodologies aim at combining solvers in static portfolios, while two methodologies are designed for the dynamic configuration of parallel portfolios. Our empirical results demonstrate that the configuration of parallel portfolios is a fruitful way for exploiting multicore machines, and that the presented approaches outperform the state of the art of parallel argumentation solvers.
LanguageEnglish
Title of host publicationAI 2017: Advances in Artificial Intelligence
Subtitle of host publication30th Australasian Joint Conference, Melbourne, VIC, Australia, August 19–20, 2017, Proceedings
EditorsWei Peng, Damminda Alahakoon, Xiaodong Li
PublisherSpringer Verlag
Pages315-327
Number of pages13
Edition1st
ISBN (Electronic)9783319630045
ISBN (Print)9783319630038
DOIs
Publication statusPublished - 9 Jul 2017
Event30th Australasian Joint Conference on Artificial Intelligence - Melbourne, Australia
Duration: 19 Aug 201720 Aug 2017
Conference number: 30
https://link.springer.com/conference/ausai (Link to Conference Website )

Publication series

NameLecture Notes in Artificial Intelligence
PublisherSpringer Verlag
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference30th Australasian Joint Conference on Artificial Intelligence
Abbreviated titleAI'17
CountryAustralia
CityMelbourne
Period19/08/1720/08/17
Internet address

Fingerprint

Availability

Cite this

Vallati, M., Cerutti, F., & Giacomin, M. (2017). On the Combination of Argumentation Solvers into Parallel Portfolios. In W. Peng, D. Alahakoon, & X. Li (Eds.), AI 2017: Advances in Artificial Intelligence: 30th Australasian Joint Conference, Melbourne, VIC, Australia, August 19–20, 2017, Proceedings (1st ed., pp. 315-327). (Lecture Notes in Artificial Intelligence). Springer Verlag. https://doi.org/10.1007%2F978-3-319-63004-5_25
Vallati, Mauro ; Cerutti, Federico ; Giacomin, Massimiliano. / On the Combination of Argumentation Solvers into Parallel Portfolios. AI 2017: Advances in Artificial Intelligence: 30th Australasian Joint Conference, Melbourne, VIC, Australia, August 19–20, 2017, Proceedings. editor / Wei Peng ; Damminda Alahakoon ; Xiaodong Li. 1st. ed. Springer Verlag, 2017. pp. 315-327 (Lecture Notes in Artificial Intelligence).
@inproceedings{306f6c1ad3334730a65bf23d85c723ad,
title = "On the Combination of Argumentation Solvers into Parallel Portfolios",
abstract = "In the light of the increasing interest in efficient algorithms for solving abstract argumentation problems and the pervasive availability of multicore machines, a natural research issue is to combine existing argumentation solvers into parallel portfolios. In this work, we introduce six methodologies for the automatic configuration of parallel portfolios of argumentation solvers for enumerating the preferred extensions of a given framework. In particular, four methodologies aim at combining solvers in static portfolios, while two methodologies are designed for the dynamic configuration of parallel portfolios. Our empirical results demonstrate that the configuration of parallel portfolios is a fruitful way for exploiting multicore machines, and that the presented approaches outperform the state of the art of parallel argumentation solvers.",
keywords = "Artificial intelligence, Learning systems, Problem solving, Genetic algorithms, Evolutionary algorithms, Support Vector Machines, Internet, Data mining, World wide web, Learning algorithms, Neural networks, User interfaces, Classifiers, Support vector, Multiobjective optimization, Pareto-optimal, Network security, Signal processing, Pareto principle, Semantic web, Argumentation reasoning, Parallel computing, Algorithm selection",
author = "Mauro Vallati and Federico Cerutti and Massimiliano Giacomin",
year = "2017",
month = "7",
day = "9",
doi = "10.1007{\%}2F978-3-319-63004-5_25",
language = "English",
isbn = "9783319630038",
series = "Lecture Notes in Artificial Intelligence",
publisher = "Springer Verlag",
pages = "315--327",
editor = "Wei Peng and Damminda Alahakoon and Xiaodong Li",
booktitle = "AI 2017: Advances in Artificial Intelligence",
edition = "1st",

}

Vallati, M, Cerutti, F & Giacomin, M 2017, On the Combination of Argumentation Solvers into Parallel Portfolios. in W Peng, D Alahakoon & X Li (eds), AI 2017: Advances in Artificial Intelligence: 30th Australasian Joint Conference, Melbourne, VIC, Australia, August 19–20, 2017, Proceedings. 1st edn, Lecture Notes in Artificial Intelligence, Springer Verlag, pp. 315-327, 30th Australasian Joint Conference on Artificial Intelligence, Melbourne, Australia, 19/08/17. https://doi.org/10.1007%2F978-3-319-63004-5_25

On the Combination of Argumentation Solvers into Parallel Portfolios. / Vallati, Mauro; Cerutti, Federico; Giacomin, Massimiliano.

AI 2017: Advances in Artificial Intelligence: 30th Australasian Joint Conference, Melbourne, VIC, Australia, August 19–20, 2017, Proceedings. ed. / Wei Peng; Damminda Alahakoon; Xiaodong Li. 1st. ed. Springer Verlag, 2017. p. 315-327 (Lecture Notes in Artificial Intelligence).

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

TY - GEN

T1 - On the Combination of Argumentation Solvers into Parallel Portfolios

AU - Vallati, Mauro

AU - Cerutti, Federico

AU - Giacomin, Massimiliano

PY - 2017/7/9

Y1 - 2017/7/9

N2 - In the light of the increasing interest in efficient algorithms for solving abstract argumentation problems and the pervasive availability of multicore machines, a natural research issue is to combine existing argumentation solvers into parallel portfolios. In this work, we introduce six methodologies for the automatic configuration of parallel portfolios of argumentation solvers for enumerating the preferred extensions of a given framework. In particular, four methodologies aim at combining solvers in static portfolios, while two methodologies are designed for the dynamic configuration of parallel portfolios. Our empirical results demonstrate that the configuration of parallel portfolios is a fruitful way for exploiting multicore machines, and that the presented approaches outperform the state of the art of parallel argumentation solvers.

AB - In the light of the increasing interest in efficient algorithms for solving abstract argumentation problems and the pervasive availability of multicore machines, a natural research issue is to combine existing argumentation solvers into parallel portfolios. In this work, we introduce six methodologies for the automatic configuration of parallel portfolios of argumentation solvers for enumerating the preferred extensions of a given framework. In particular, four methodologies aim at combining solvers in static portfolios, while two methodologies are designed for the dynamic configuration of parallel portfolios. Our empirical results demonstrate that the configuration of parallel portfolios is a fruitful way for exploiting multicore machines, and that the presented approaches outperform the state of the art of parallel argumentation solvers.

KW - Artificial intelligence

KW - Learning systems

KW - Problem solving

KW - Genetic algorithms

KW - Evolutionary algorithms

KW - Support Vector Machines

KW - Internet

KW - Data mining

KW - World wide web

KW - Learning algorithms

KW - Neural networks

KW - User interfaces

KW - Classifiers

KW - Support vector

KW - Multiobjective optimization

KW - Pareto-optimal

KW - Network security

KW - Signal processing

KW - Pareto principle

KW - Semantic web

KW - Argumentation reasoning

KW - Parallel computing

KW - Algorithm selection

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85026758078&origin=resultslist&sort=plf-f&src=s&st1=On+the+Combination+of+Argumentation+Solvers+into+Parallel+Portfolios&st2=&sid=f5407c8a6ad1ae2368e1f5f825950a4e&sot=b&sdt=b&sl=83&s=TITLE-ABS-KEY%28On+the+Combination+of+Argumentation+Solvers+into+Parallel+Portfolios%29&relpos=0&citeCnt=0&searchTerm=

U2 - 10.1007%2F978-3-319-63004-5_25

DO - 10.1007%2F978-3-319-63004-5_25

M3 - Conference contribution

SN - 9783319630038

T3 - Lecture Notes in Artificial Intelligence

SP - 315

EP - 327

BT - AI 2017: Advances in Artificial Intelligence

A2 - Peng, Wei

A2 - Alahakoon, Damminda

A2 - Li, Xiaodong

PB - Springer Verlag

ER -

Vallati M, Cerutti F, Giacomin M. On the Combination of Argumentation Solvers into Parallel Portfolios. In Peng W, Alahakoon D, Li X, editors, AI 2017: Advances in Artificial Intelligence: 30th Australasian Joint Conference, Melbourne, VIC, Australia, August 19–20, 2017, Proceedings. 1st ed. Springer Verlag. 2017. p. 315-327. (Lecture Notes in Artificial Intelligence). https://doi.org/10.1007%2F978-3-319-63004-5_25