Deutsch
 
Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  HPExplorer: XAI Method to Explore the Relationship Between Hyperparameters and Model Performance

Grushetskaya, Y., Sips, M., Schachtschneider, R., Saberioon, M., Mahan, A. (2024): HPExplorer: XAI Method to Explore the Relationship Between Hyperparameters and Model Performance. - In: Bifet, A., Krilavičius, T., Miliou, I., Nowaczyk, S. (Eds.), Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track, (Lecture Notes in Computer Science ; 14949), Cham : Springer Nature Switzerland, 319-334.
https://doi.org/10.1007/978-3-031-70378-2_20

Item is

Externe Referenzen

einblenden:

Urheber

einblenden:
ausblenden:
 Urheber:
Grushetskaya, Yulia1, 2, Autor              
Sips, M.1, Autor              
Schachtschneider, Reyko3, Autor              
Saberioon, Mohammadmehdi1, Autor              
Mahan, Akram1, Autor              
Affiliations:
11.4 Remote Sensing, 1.0 Geodesy, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum, ou_146028              
2Submitting Corresponding Author, Deutsches GeoForschungsZentrum, ou_5026390              
31.3 Earth System Modelling, 1.0 Geodesy, Departments, GFZ Publication Database, Deutsches GeoForschungsZentrum, ou_146027              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: Hyperparameters (HPs) play a central role in the performance of machine learning (ML) models, governing model structure, regularization, and convergence properties. Understanding the intricate relationship between HP configurations and model performance is essential for ML practitioners, especially those with limited expertise, to develop effective models that produce satisfactory results. This paper introduces HyperParameter Explorer (HPExplorer), a semi-automated eXplainable AI (XAI) method, to support ML practitioners to explore this relationship. HPExplorer integrates an automated HP discovery algorithm with an interactive visual exploration component. The HP discovery algorithm identifies performance-consistent subspaces within the HP space, where models perform similarly despite minor variations in HP configurations. The interactive visual exploration component enables users to explore the discovered performance-consistent subspaces using an interactive 2-D projection called Star Coordinate. Users can also compare HP configurations from different subspaces to explore their impact on model performance. We developed HPExplorer in close collaboration with ML practitioners, particularly geoscientists, using ML in their research. Initial feedback from scientists using HPExplorer in real-world scenarios indicates that HPExploer enhances the transparency in configuring HPs and increases the confidence of users in their decisions.

Details

einblenden:
ausblenden:
Sprache(n): eng - Englisch
 Datum: 2024-08-222024
 Publikationsstatus: Final veröffentlicht
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: DOI: 10.1007/978-3-031-70378-2_20
GFZPOF: p4 T5 Future Landscapes
GFZPOFWEITERE: p4 T2 Ocean and Cryosphere
 Art des Abschluß: -

Veranstaltung

einblenden:

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Machine Learning and Knowledge Discovery in Databases. Applied Data Science Track
Genre der Quelle: Buch
 Urheber:
Bifet, Albert1, Herausgeber
Krilavičius, Tomas1, Herausgeber
Miliou, Ioanna1, Herausgeber
Nowaczyk, Slawomir1, Herausgeber
Affiliations:
1 External Organizations, ou_persistent22            
Ort, Verlag, Ausgabe: Cham : Springer Nature Switzerland
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 319 - 334 Identifikator: ISSN: 0302-9743
ISSN: 1611-3349
ISBN: 978-3-031-70377-5
ISBN: 978-3-031-70378-2

Quelle 2

einblenden:
ausblenden:
Titel: Lecture Notes in Computer Science
Genre der Quelle: Reihe
 Urheber:
Affiliations:
Ort, Verlag, Ausgabe: -
Seiten: - Band / Heft: 14949 Artikelnummer: - Start- / Endseite: - Identifikator: -