search

Allen0307 / AdapterBias

Code for the Findings of NAACL 2022(Long Paper): AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks
18 stars 0 forks source link

Can't find L0 regularization implementation. #1

Closed pantianrui closed 1 year ago

pantianrui commented 1 year ago

Hello, I cannot find the implementation of L0 regularization, which is mentioned in your paper. Could you please show me where it is?

Allen0307 commented 1 year ago

Hi, Alice. Our implementation of L0 regularization is the same as diff-pruning(https://arxiv.org/abs/2012.07463). The similar code could be found in here(https://github.com/dguo98/DiffPruning/blob/main/examples/run_glue_diffpruning.py). Thanks!