Vogel, Liane ; Hilprecht, Benjamin ; Binnig, Carsten (2022)
Towards Foundation Models for Relational Databases Vision Paper.
36th Conference on Neural Information Processing Systems (NeurIPS 2022). New Orleans, USA (28.11.2022-09.12.2022)
Konferenzveröffentlichung, Bibliographie
Kurzbeschreibung (Abstract)
Tabular representation learning has recently gained a lot of attention. However, existing approaches only learn a representation from a single table, and thus ignore the potential to learn from the full structure of relational databases, including neighboring tables that can contain important information for a contextualized representation. Moreover, current models are significantly limited in scale, which prevents that they learn from large databases. In this paper, we thus introduce our vision of relational representation learning, that can not only learn from the full relational structure, but also can scale to larger database sizes that are commonly found in real-world. Moreover, we also discuss opportunities and challenges we see along the way to enable this vision and present initial very promising results. Overall, we argue that this direction can lead to foundation models for relational databases that are today only available for text and images.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Vogel, Liane ; Hilprecht, Benjamin ; Binnig, Carsten |
| Art des Eintrags: | Bibliographie |
| Titel: | Towards Foundation Models for Relational Databases Vision Paper |
| Sprache: | Englisch |
| Publikationsjahr: | 10 Dezember 2022 |
| Veranstaltungstitel: | 36th Conference on Neural Information Processing Systems (NeurIPS 2022) |
| Veranstaltungsort: | New Orleans, USA |
| Veranstaltungsdatum: | 28.11.2022-09.12.2022 |
| URL / URN: | https://openreview.net/forum?id=s1KlNOQq71_ |
| Kurzbeschreibung (Abstract): | Tabular representation learning has recently gained a lot of attention. However, existing approaches only learn a representation from a single table, and thus ignore the potential to learn from the full structure of relational databases, including neighboring tables that can contain important information for a contextualized representation. Moreover, current models are significantly limited in scale, which prevents that they learn from large databases. In this paper, we thus introduce our vision of relational representation learning, that can not only learn from the full relational structure, but also can scale to larger database sizes that are commonly found in real-world. Moreover, we also discuss opportunities and challenges we see along the way to enable this vision and present initial very promising results. Overall, we argue that this direction can lead to foundation models for relational databases that are today only available for text and images. |
| Freie Schlagworte: | dm_nhr4ces |
| Zusätzliche Informationen: | Table Representation Learning Workshop at NeurIPS 2022 |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Data and AI Systems |
| Hinterlegungsdatum: | 08 Feb 2023 08:53 |
| Letzte Änderung: | 08 Feb 2023 08:53 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum