SparseAdapter: An Easy Approach for Improving the Parameter-Efficiency of Adapters. (arXiv:2210.04284v5 [cs.CL] UPDATED)

Adapter Tuning, which freezes the pretrained language models (PLMs) and only
fine-tunes a few extra modules, becomes an appealing efficient alternative to
the full model fine-tuning. Although computationally efficient, the recent
Adapters often increase parameters (e.g. bottleneck dimension) for matching the
performance of full model fine-tuning, which we argue goes against their
original intention. In this work, we re-examine the parameter-efficiency of
Adapters through the lens of network pruning (we name such plug-in concept as
\texttt{SparseAdapter}) and find that SparseAdapter …

arxiv easy efficiency