Wehrstein, Johannes ; Hilprecht, Benjamin ; Olt, Benjamin ; Luthra, Manisha ; Binnig, Carsten (2022)
The Case for Multi-Task Zero-Shot Learning for Databases.
4th International Workshop on Applied AI for Database Systems and Applications. Sydney, Australia (05.09.2022-05.09.2022)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Recently, machine learning has successfully been applied to many database problems such as query optimization, physical design tuning, or cardinality estimation. However, the predominant paradigm to design such learned database components is workload-driven learning, where a representative workload has to be executed on the database to gather training data. This costly procedure has to be repeated for every new database a model should be trained on. Hence, recently it was suggested to train zero-shot cost models that are pretrained once and can generalize to unseen databases out-of-the-box. While the results for the task of cost estimation are promising, it is unclear how to generalize this approach to additional tasks beyond query latency prediction. Hence, in this paper, we propose several directions to generalize zero-shot cost models to other tasks and validate our approaches in two case studies.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Wehrstein, Johannes ; Hilprecht, Benjamin ; Olt, Benjamin ; Luthra, Manisha ; Binnig, Carsten |
| Art des Eintrags: | Bibliographie |
| Titel: | The Case for Multi-Task Zero-Shot Learning for Databases |
| Sprache: | Englisch |
| Publikationsjahr: | 5 September 2022 |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | AIDB2022 |
| Veranstaltungstitel: | 4th International Workshop on Applied AI for Database Systems and Applications |
| Veranstaltungsort: | Sydney, Australia |
| Veranstaltungsdatum: | 05.09.2022-05.09.2022 |
| Zugehörige Links: | |
| Kurzbeschreibung (Abstract): | Recently, machine learning has successfully been applied to many database problems such as query optimization, physical design tuning, or cardinality estimation. However, the predominant paradigm to design such learned database components is workload-driven learning, where a representative workload has to be executed on the database to gather training data. This costly procedure has to be repeated for every new database a model should be trained on. Hence, recently it was suggested to train zero-shot cost models that are pretrained once and can generalize to unseen databases out-of-the-box. While the results for the task of cost estimation are promising, it is unclear how to generalize this approach to additional tasks beyond query latency prediction. Hence, in this paper, we propose several directions to generalize zero-shot cost models to other tasks and validate our approaches in two case studies. |
| Freie Schlagworte: | systems_maki, systems_funding_52115350, databases, ml, learned database components, zero-shot learning, MV selection, ML4DB |
| Zusätzliche Informationen: | Held with VLDB 2022 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Data and AI Systems |
| TU-Projekte: | DFG|SFB1053|SFB1053 TPZ Steinmet |
| Hinterlegungsdatum: | 04 Apr 2023 12:48 |
| Letzte Änderung: | 04 Apr 2023 12:48 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum