LPLgrad trains a main classifier with an auxiliary loss-prediction module and queries samples by entropy gradient norm, yielding modest accuracy gains over existing active learning baselines.
Verips: Verified pseudo- label selection for deep active learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
LPLgrad: Optimizing Active Learning Through Gradient Norm Sample Selection and Auxiliary Model Training
LPLgrad trains a main classifier with an auxiliary loss-prediction module and queries samples by entropy gradient norm, yielding modest accuracy gains over existing active learning baselines.