Geisler, Nadja ; Hättasch, Benjamin ; Binnig, Carsten (2022)
Demonstrating Quest: A Query-Driven Framework to Explain Classification Models on Tabular Data.
In: Proceedings of the VLDB Endowment, 15 (12)
doi: 10.14778/3554821.3554884
Artikel, Bibliographie
Kurzbeschreibung (Abstract)
Machine learning models are everywhere now; but only few of them are transparent in how they work. To remedy this, local explanations aim to show users how and why learned models produce a certain output for a given input (data sample). However, most existing approaches are oriented around images or text data and, thus, cannot leverage the structure and properties of tabular data. Therefore, we demonstrate Quest, a new framework for generating explanations that are a better fit for tabular data. The main idea is to create explanations in the form of relational predicates (called queries hereafter) that approximate the behavior of a classifier around the given sample. For this demo, we use Quest on different synthetic and real-world tabular data sets and pair it with a user interface intended to be used during model development by a data scientist working on classification models.
| Typ des Eintrags: | Artikel |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Geisler, Nadja ; Hättasch, Benjamin ; Binnig, Carsten |
| Art des Eintrags: | Bibliographie |
| Titel: | Demonstrating Quest: A Query-Driven Framework to Explain Classification Models on Tabular Data |
| Sprache: | Englisch |
| Publikationsjahr: | 1 August 2022 |
| Verlag: | ACM |
| Titel der Zeitschrift, Zeitung oder Schriftenreihe: | Proceedings of the VLDB Endowment |
| Jahrgang/Volume einer Zeitschrift: | 15 |
| (Heft-)Nummer: | 12 |
| DOI: | 10.14778/3554821.3554884 |
| Kurzbeschreibung (Abstract): | Machine learning models are everywhere now; but only few of them are transparent in how they work. To remedy this, local explanations aim to show users how and why learned models produce a certain output for a given input (data sample). However, most existing approaches are oriented around images or text data and, thus, cannot leverage the structure and properties of tabular data. Therefore, we demonstrate Quest, a new framework for generating explanations that are a better fit for tabular data. The main idea is to create explanations in the form of relational predicates (called queries hereafter) that approximate the behavior of a classifier around the given sample. For this demo, we use Quest on different synthetic and real-world tabular data sets and pair it with a user interface intended to be used during model development by a data scientist working on classification models. |
| Freie Schlagworte: | systems_quest, systems_funding_50001242, systems_kompaki |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Data and AI Systems |
| Hinterlegungsdatum: | 06 Jun 2023 12:26 |
| Letzte Änderung: | 02 Aug 2023 12:38 |
| PPN: | 510086489 |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum