GALE aggregates local explanations to reveal global model behavior, showing that LIME's global importance measure is unreliable while the proposed aggregations better capture how features affect predictions.
arXiv preprint arXiv:1901.04592 (2019)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.
citing papers explorer
-
Global Aggregations of Local Explanations for Black Box models
GALE aggregates local explanations to reveal global model behavior, showing that LIME's global importance measure is unreliable while the proposed aggregations better capture how features affect predictions.
-
Explainable AI for Jet Tagging: A Comparative Study of GNNExplainer, GNNShap, and GradCAM for Jet Tagging in the Lund Jet Plane
Explainability techniques applied to LundNet show that assigned node importance correlates with classical jet substructure observables such as N-subjettiness ratios and energy correlation functions, with shifts across transverse-momentum regimes.