TU Darmstadt / ULB / TUbiblio

On the Trade-Off Between Consistency and Coverage in Multi-label Rule Learning Heuristics

Rapp, Michael ; Loza Mencía, Eneldo ; Fürnkranz, Johannes
Kralj Novak, Petra ; Šmuc, Tomislav ; Džeroski, Sašo (eds.) (2019):
On the Trade-Off Between Consistency and Coverage in Multi-label Rule Learning Heuristics.
pp. 96-111, DS'19 - 22nd International Conference on Discovery Science, Split, Croatia, October 28.–30., 2019, ISBN 978-3-030-33778-0,
DOI: 10.1007/978-3-030-33778-0_9,
[Conference or Workshop Item]

Abstract

Recently, several authors have advocated the use of rule learning algorithms to model multi-label data, as rules are interpretable and can be comprehended, analyzed, or qualitatively evaluated by domain experts. Many rule learning algorithms employ a heuristic-guided search for rules that model regularities contained in the training data and it is commonly accepted that the choice of the heuristic has a significant impact on the predictive performance of the learner. Whereas the properties of rule learning heuristics have been studied in the realm of single-label classification, there is no such work taking into account the particularities of multi-label classification. This is surprising, as the quality of multi-label predictions is usually assessed in terms of a variety of different, potentially competing, performance measures that cannot all be optimized by a single learner at the same time. In this work, we show empirically that it is crucial to trade off the consistency and coverage of rules differently, depending on which multi-label measure should be optimized by a model. Based on these findings, we emphasize the need for configurable learners that can flexibly use different heuristics. As our experiments reveal, the choice of the heuristic is not straight-forward, because a search for rules that optimize a measure locally does usually not result in a model that maximizes that measure globally.

Item Type: Conference or Workshop Item
Erschienen: 2019
Editors: Kralj Novak, Petra ; Šmuc, Tomislav ; Džeroski, Sašo
Creators: Rapp, Michael ; Loza Mencía, Eneldo ; Fürnkranz, Johannes
Title: On the Trade-Off Between Consistency and Coverage in Multi-label Rule Learning Heuristics
Language: English
Abstract:

Recently, several authors have advocated the use of rule learning algorithms to model multi-label data, as rules are interpretable and can be comprehended, analyzed, or qualitatively evaluated by domain experts. Many rule learning algorithms employ a heuristic-guided search for rules that model regularities contained in the training data and it is commonly accepted that the choice of the heuristic has a significant impact on the predictive performance of the learner. Whereas the properties of rule learning heuristics have been studied in the realm of single-label classification, there is no such work taking into account the particularities of multi-label classification. This is surprising, as the quality of multi-label predictions is usually assessed in terms of a variety of different, potentially competing, performance measures that cannot all be optimized by a single learner at the same time. In this work, we show empirically that it is crucial to trade off the consistency and coverage of rules differently, depending on which multi-label measure should be optimized by a model. Based on these findings, we emphasize the need for configurable learners that can flexibly use different heuristics. As our experiments reveal, the choice of the heuristic is not straight-forward, because a search for rules that optimize a measure locally does usually not result in a model that maximizes that measure globally.

ISBN: 978-3-030-33778-0
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Knowl­edge En­gi­neer­ing
Event Title: DS'19 - 22nd International Conference on Discovery Science
Event Location: Split, Croatia
Event Dates: October 28.–30., 2019
Date Deposited: 18 Dec 2019 10:43
DOI: 10.1007/978-3-030-33778-0_9
Export:
Suche nach Titel in: TUfind oder in Google
Send an inquiry Send an inquiry

Options (only for editors)
Show editorial Details Show editorial Details