GhostRNN compresses RNN hidden states by generating ghost states from a small set of intrinsic states with cheap linear operations, cutting parameters by about 40% with similar accuracy.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
GhostRNN: Reducing State Redundancy in RNN with Cheap Operations
GhostRNN compresses RNN hidden states by generating ghost states from a small set of intrinsic states with cheap linear operations, cutting parameters by about 40% with similar accuracy.