SUBPLEX: A Visual Analytics Approach to Understand Local Model Explanations at the Subpopulation Level



Jun Yuan, Gromit Yeuk-Yin Chan, Brian Barr, Kyle Overton, Kim Rees, Luis Gustavo Nonato, Enrico Bertini, Claudio Silva

 Room: 104

Wednesday, October 25th, 2023 @ 00:21GMT+00:00Change your timezone on the schedule page
2 years agoYour current time: Saturday, May 17th @ 17:21

Exemplar figure, described by caption below — SUBPLEX is a visual analytics tool in Jupyter notebook to assist data scientist to understand local model explanations at the subpopulation level. SUBPLEX contains five linked views: (a) code block, (b) cluster refinement view, (c) projection view, (d) subpopulation creation panel, (e) local explanation detail view.

Fast forward

Full Video

Abstract