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.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
DSCF is a deep social collaborative filtering model that uses distant neighbors and item-relevant opinions from social networks to improve recommendation accuracy over prior deep models.
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.
-
Deep Social Collaborative Filtering
DSCF is a deep social collaborative filtering model that uses distant neighbors and item-relevant opinions from social networks to improve recommendation accuracy over prior deep models.