Hilprecht, Benjamin ; Binnig, Carsten (2022)
One Model to Rule them All: Towards Zero-Shot Learning for Databases.
12th Annual Conference on Innovative Data Systems Research (CIDR'22). Chaminade, USA (09.-12.01.2022)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
In this paper, we present our vision of so called zero-shot learn- ing for databases which is a new learning approach for database components. Zero-shot learning for databases is inspired by recent advances in transfer learning of models such as GPT-3 and can support a new database out-of-the box without the need to train a new model. Furthermore, it can easily be extended to few-shot learning by further retraining the model on the unseen database. As a first concrete contribution in this paper, we show the feasi- bility of zero-shot learning for the task of physical cost estimation and present very promising initial results. Moreover, as a second contribution we discuss the core challenges related to zero-shot learning for databases and present a roadmap to extend zero-shot learning towards many other tasks beyond cost estimation or even beyond classical database systems and workloads.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Hilprecht, Benjamin ; Binnig, Carsten |
| Art des Eintrags: | Bibliographie |
| Titel: | One Model to Rule them All: Towards Zero-Shot Learning for Databases |
| Sprache: | Englisch |
| Publikationsjahr: | 14 Dezember 2022 |
| Veranstaltungstitel: | 12th Annual Conference on Innovative Data Systems Research (CIDR'22) |
| Veranstaltungsort: | Chaminade, USA |
| Veranstaltungsdatum: | 09.-12.01.2022 |
| Kurzbeschreibung (Abstract): | In this paper, we present our vision of so called zero-shot learn- ing for databases which is a new learning approach for database components. Zero-shot learning for databases is inspired by recent advances in transfer learning of models such as GPT-3 and can support a new database out-of-the box without the need to train a new model. Furthermore, it can easily be extended to few-shot learning by further retraining the model on the unseen database. As a first concrete contribution in this paper, we show the feasi- bility of zero-shot learning for the task of physical cost estimation and present very promising initial results. Moreover, as a second contribution we discuss the core challenges related to zero-shot learning for databases and present a roadmap to extend zero-shot learning towards many other tasks beyond cost estimation or even beyond classical database systems and workloads. |
| Zusätzliche Informationen: | More Information at http://www.cidrdb.org/cidr2022/index.html |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Data Management (2022 umbenannt in Data and AI Systems) DFG-Sonderforschungsbereiche (inkl. Transregio) DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet > C: Kommunikationsmechanismen DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1053: MAKI – Multi-Mechanismen-Adaption für das künftige Internet > C: Kommunikationsmechanismen > Teilprojekt C2: Informationszentrische Sicht |
| Hinterlegungsdatum: | 21 Apr 2022 07:57 |
| Letzte Änderung: | 21 Apr 2022 07:57 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum