Rapp, Michael ; Loza Mencía, Johannes
Hrsg.: Phung, Dinh ; Tseng, Vincent S. ; Webb, Geoffrey I. ; Ho, Bao ; Ganji, Mohadeseh ; Rashidi, Lida (2018)
Exploiting Anti-monotonicity of Multi-label Evaluation Measures for Inducing Multi-label Rules.
Advances in Knowledge Discovery and Data Mining. Cham
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Exploiting dependencies between labels is considered to be crucial for multi-label classification. Rules are able to expose label dependencies such as implications, subsumptions or exclusions in a human-comprehensible and interpretable manner. However, the induction of rules with multiple labels in the head is particularly challenging, as the number of label combinations which must be taken into account for each rule grows exponentially with the number of available labels. To overcome this limitation, algorithms for exhaustive rule mining typically use properties such as anti-monotonicity or decomposability in order to prune the search space. In the present paper, we examine whether commonly used multi-label evaluation metrics satisfy these properties and therefore are suited to prune the search space for multi-label heads.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2018 |
| Herausgeber: | Phung, Dinh ; Tseng, Vincent S. ; Webb, Geoffrey I. ; Ho, Bao ; Ganji, Mohadeseh ; Rashidi, Lida |
| Autor(en): | Rapp, Michael ; Loza Mencía, Johannes |
| Art des Eintrags: | Bibliographie |
| Titel: | Exploiting Anti-monotonicity of Multi-label Evaluation Measures for Inducing Multi-label Rules |
| Sprache: | Deutsch |
| Publikationsjahr: | 2018 |
| Ort: | Cham |
| Verlag: | Springer International Publishing |
| Veranstaltungstitel: | Advances in Knowledge Discovery and Data Mining |
| Veranstaltungsort: | Cham |
| Kurzbeschreibung (Abstract): | Exploiting dependencies between labels is considered to be crucial for multi-label classification. Rules are able to expose label dependencies such as implications, subsumptions or exclusions in a human-comprehensible and interpretable manner. However, the induction of rules with multiple labels in the head is particularly challenging, as the number of label combinations which must be taken into account for each rule grows exponentially with the number of available labels. To overcome this limitation, algorithms for exhaustive rule mining typically use properties such as anti-monotonicity or decomposability in order to prune the search space. In the present paper, we examine whether commonly used multi-label evaluation metrics satisfy these properties and therefore are suited to prune the search space for multi-label heads. |
| Fachbereich(e)/-gebiet(e): | DFG-Graduiertenkollegs DFG-Graduiertenkollegs > Graduiertenkolleg 1994 Adaptive Informationsaufbereitung aus heterogenen Quellen |
| Hinterlegungsdatum: | 23 Okt 2018 13:56 |
| Letzte Änderung: | 23 Okt 2018 13:56 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum