ExplainExplore: Visual Exploration of Machine Learning Explanations

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

32 Citations (Scopus)
1420 Downloads (Pure)


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.
Original languageEnglish
Title of host publication2020 IEEE Pacific Visualization Symposium, PacificVis 2020 - Proceedings
EditorsFabian Beck, Jinwook Seo, Chaoli Wang
PublisherInstitute of Electrical and Electronics Engineers
Number of pages10
ISBN (Electronic)978-1-7281-5697-2
Publication statusPublished - 3 Jun 2020
Event13th IEEE Pacific Visualization Symposium, PacificVis 2020 - Tianjin, China
Duration: 14 Apr 202017 Apr 2020


Conference13th IEEE Pacific Visualization Symposium, PacificVis 2020


  • Computing methodologies
  • Human-centered computing
  • Machine learning
  • Visualization


Dive into the research topics of 'ExplainExplore: Visual Exploration of Machine Learning Explanations'. Together they form a unique fingerprint.

Cite this