Knowledge distillation most benefits intermediate-complexity students for time series classification, cutting parameters sharply while matching teacher accuracy across FCN, Inception, and ConvTran on UCR.
International conference on data mining (ICDM) 123 215 Page 22 of 24 J
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing deep learning models for time series classification via knowledge distillation
Knowledge distillation most benefits intermediate-complexity students for time series classification, cutting parameters sharply while matching teacher accuracy across FCN, Inception, and ConvTran on UCR.