Geisler, Nadja ; Binnig, Carsten (2022)
Introducing Quest: A Query-Driven Framework to Explain Classification Models on Tabular Data.
SIGMOD/PODS '22: International Conference on Management of Data. Philadelphia, Pennsylvania (12.06.2022)
doi: 10.1145/3546930.3547497
Konferenzveröffentlichung, 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 for are oriented around images or text data and, thus, cannot leverage the structure and properties of tabular data. Therefore, we present 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. In an initial evaluation, we show anecdotally how Quest can be used on a tabular data set compared to existing approaches that can be applied on tabular data.
| Typ des Eintrags: | Konferenzveröffentlichung |
|---|---|
| Erschienen: | 2022 |
| Autor(en): | Geisler, Nadja ; Binnig, Carsten |
| Art des Eintrags: | Bibliographie |
| Titel: | Introducing Quest: A Query-Driven Framework to Explain Classification Models on Tabular Data |
| Sprache: | Englisch |
| Publikationsjahr: | 17 August 2022 |
| Verlag: | ACM |
| Buchtitel: | HILDA '22: Proceedings of the Workshop on Human-In-the-Loop Data Analytics |
| Veranstaltungstitel: | SIGMOD/PODS '22: International Conference on Management of Data |
| Veranstaltungsort: | Philadelphia, Pennsylvania |
| Veranstaltungsdatum: | 12.06.2022 |
| DOI: | 10.1145/3546930.3547497 |
| 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 for are oriented around images or text data and, thus, cannot leverage the structure and properties of tabular data. Therefore, we present 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. In an initial evaluation, we show anecdotally how Quest can be used on a tabular data set compared to existing approaches that can be applied on tabular data. |
| Freie Schlagworte: | systems_quest, systems_funding_50001242, systems_kompaki, tabular data, local post-hoc explanations, surrogate models, interpretability, explainable AI, classification |
| Fachbereich(e)/-gebiet(e): | 20 Fachbereich Informatik 20 Fachbereich Informatik > Data and AI Systems |
| Hinterlegungsdatum: | 06 Jun 2023 12:28 |
| Letzte Änderung: | 06 Jun 2023 12:28 |
| PPN: | |
| Export: | |
| Suche nach Titel in: | TUfind oder in Google |
 |
Frage zum Eintrag |
Optionen (nur für Redakteure)
 |
Redaktionelle Details anzeigen |
Drucken
Impressum