Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387130605> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W4387130605 abstract "In the last ten years, various automated machine learning (AutoML) systems have been proposed to build end-to-end machine learning (ML) pipelines with minimal human interaction. Even though such automatically synthesized ML pipelines are able to achieve competitive performance, recent studies have shown that users do not trust models constructed by AutoML due to missing transparency of AutoML systems and missing explanations for the constructed ML pipelines. In a requirements analysis study with 36 domain experts, data scientists, and AutoML researchers from different professions with vastly different expertise in ML, we collect detailed informational needs for AutoML. We propose XAutoML, an interactive visual analytics tool for explaining arbitrary AutoML optimization procedures and ML pipelines constructed by AutoML. XAutoML combines interactive visualizations with established techniques from explainable artificial intelligence (XAI) to make the complete AutoML procedure transparent and explainable. By integrating XAutoML with JupyterLab, experienced users can extend the visual analytics with ad-hoc visualizations based on information extracted from XAutoML. We validate our approach in a user study with the same diverse user group from the requirements analysis. All participants were able to extract useful information from XAutoML, leading to a significantly increased understanding of ML pipelines produced by AutoML and the AutoML optimization itself." @default.
- W4387130605 created "2023-09-29" @default.
- W4387130605 creator A5026706797 @default.
- W4387130605 creator A5031354877 @default.
- W4387130605 creator A5036814342 @default.
- W4387130605 creator A5091898246 @default.
- W4387130605 date "2023-09-28" @default.
- W4387130605 modified "2023-10-18" @default.
- W4387130605 title "XAutoML: A Visual Analytics Tool for Understanding and Validating Automated Machine Learning" @default.
- W4387130605 cites W1678356000 @default.
- W4387130605 cites W2032191478 @default.
- W4387130605 cites W2125847307 @default.
- W4387130605 cites W2135415614 @default.
- W4387130605 cites W2146292423 @default.
- W4387130605 cites W2294798173 @default.
- W4387130605 cites W2751110224 @default.
- W4387130605 cites W2788403449 @default.
- W4387130605 cites W2809880372 @default.
- W4387130605 cites W2911964244 @default.
- W4387130605 cites W2950680102 @default.
- W4387130605 cites W2963305465 @default.
- W4387130605 cites W2997591727 @default.
- W4387130605 cites W3083082685 @default.
- W4387130605 cites W3092425241 @default.
- W4387130605 cites W3100032425 @default.
- W4387130605 cites W3101981467 @default.
- W4387130605 cites W3123920941 @default.
- W4387130605 cites W3138819813 @default.
- W4387130605 cites W3197347140 @default.
- W4387130605 cites W4205110562 @default.
- W4387130605 doi "https://doi.org/10.1145/3625240" @default.
- W4387130605 hasPublicationYear "2023" @default.
- W4387130605 type Work @default.
- W4387130605 citedByCount "1" @default.
- W4387130605 crossrefType "journal-article" @default.
- W4387130605 hasAuthorship W4387130605A5026706797 @default.
- W4387130605 hasAuthorship W4387130605A5031354877 @default.
- W4387130605 hasAuthorship W4387130605A5036814342 @default.
- W4387130605 hasAuthorship W4387130605A5091898246 @default.
- W4387130605 hasBestOaLocation W43871306051 @default.
- W4387130605 hasConcept C119857082 @default.
- W4387130605 hasConcept C134306372 @default.
- W4387130605 hasConcept C154945302 @default.
- W4387130605 hasConcept C2522767166 @default.
- W4387130605 hasConcept C2780233690 @default.
- W4387130605 hasConcept C33923547 @default.
- W4387130605 hasConcept C36464697 @default.
- W4387130605 hasConcept C36503486 @default.
- W4387130605 hasConcept C38652104 @default.
- W4387130605 hasConcept C41008148 @default.
- W4387130605 hasConcept C59732488 @default.
- W4387130605 hasConcept C79158427 @default.
- W4387130605 hasConceptScore W4387130605C119857082 @default.
- W4387130605 hasConceptScore W4387130605C134306372 @default.
- W4387130605 hasConceptScore W4387130605C154945302 @default.
- W4387130605 hasConceptScore W4387130605C2522767166 @default.
- W4387130605 hasConceptScore W4387130605C2780233690 @default.
- W4387130605 hasConceptScore W4387130605C33923547 @default.
- W4387130605 hasConceptScore W4387130605C36464697 @default.
- W4387130605 hasConceptScore W4387130605C36503486 @default.
- W4387130605 hasConceptScore W4387130605C38652104 @default.
- W4387130605 hasConceptScore W4387130605C41008148 @default.
- W4387130605 hasConceptScore W4387130605C59732488 @default.
- W4387130605 hasConceptScore W4387130605C79158427 @default.
- W4387130605 hasLocation W43871306051 @default.
- W4387130605 hasOpenAccess W4387130605 @default.
- W4387130605 hasPrimaryLocation W43871306051 @default.
- W4387130605 hasRelatedWork W2066992345 @default.
- W4387130605 hasRelatedWork W212334026 @default.
- W4387130605 hasRelatedWork W2148525144 @default.
- W4387130605 hasRelatedWork W2181693928 @default.
- W4387130605 hasRelatedWork W2765161871 @default.
- W4387130605 hasRelatedWork W2811283511 @default.
- W4387130605 hasRelatedWork W3012440071 @default.
- W4387130605 hasRelatedWork W3100746587 @default.
- W4387130605 hasRelatedWork W3209087738 @default.
- W4387130605 hasRelatedWork W4234269430 @default.
- W4387130605 isParatext "false" @default.
- W4387130605 isRetracted "false" @default.
- W4387130605 workType "article" @default.