ExplainExplore: Visual Exploration of Machine Learning Explanations

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

9 Citaten (Scopus)
1023 Downloads (Pure)

Samenvatting

Machine learning models often exhibit complex behavior that is difficult to understand. Recent research in explainable AI has produced promising techniques to explain the inner workings of such models using feature contribution vectors. These vectors are helpful in a wide variety of applications. However, there are many parameters involved in this process and determining which settings are best is difficult due to the subjective nature of evaluating interpretability.
To this end, we introduce ExplainExplore: an interactive explanation system to explore explanations that fit the subjective preference of data scientists. We leverage the domain knowledge of the data scientist to find optimal parameter settings and instance perturbations, and enable the discussion of the model and its explanation with domain experts.
We present a use case on a real-world dataset to demonstrate the effectiveness of our approach for the exploration and tuning of machine learning explanations.
Originele taal-2Engels
Titel2020 IEEE Pacific Visualization Symposium, PacificVis 2020 - Proceedings
RedacteurenFabian Beck, Jinwook Seo, Chaoli Wang
UitgeverijInstitute of Electrical and Electronics Engineers
Pagina's26-35
Aantal pagina's10
ISBN van elektronische versie978-1-7281-5697-2
DOI's
StatusGepubliceerd - 3 jun 2020
Evenement13th IEEE Pacific Visualization Symposium, PacificVis 2020 - Tianjin, China
Duur: 14 apr 202017 apr 2020

Congres

Congres13th IEEE Pacific Visualization Symposium, PacificVis 2020
Land/RegioChina
StadTianjin
Periode14/04/2017/04/20

Vingerafdruk

Duik in de onderzoeksthema's van 'ExplainExplore: Visual Exploration of Machine Learning Explanations'. Samen vormen ze een unieke vingerafdruk.

Citeer dit