Methods › Natural Language Processing › Autoencoding Transformers › DynaBERT
DynaBERT
Introduced by Lu Hou et al. in DynaBERT: Dynamic BERT with Adaptive Width and Depth
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
DynaBERT is a BERT-variant which can flexibly adjust the size and latency by selecting adaptive width and depth. The training process of DynaBERT includes first training a width-adaptive BERT and then allowing both adaptive width and depth, by distilling knowledge from the full-sized model to small sub-networks. Network rewiring is also used to keep the more important attention heads and neurons shared by more sub-networks.
A two-stage procedure is used to train DynaBERT. First, using knowledge distillation (dashed lines) to transfer the knowledge from a fixed teacher model to student sub-networks with adaptive width in DynaBERTW. Then, using knowledge distillation (dashed lines) to transfer the knowledge from a trained DynaBERTW to student sub-networks with adaptive width and depth in DynaBERT.
Papers archive 2025-07-28
2 shown of 2, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
Distilling Linguistic Context for Language Model Compression 17 Sep 2021 · 1 repository · arXiv:2109.08359Syntology ran 2 of 11 samples · 9 unverified
-
DynaBERT: Dynamic BERT with Adaptive Width and Depth 8 Apr 2020 · 3 repositories · arXiv:2004.04037Syntology ran 5 of 8 samples · 3 unverified · 8 pointer-only (licence)
Tasks archive 2025-07-28
7 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Language Modeling | 2 |
| Language Modelling | 2 |
| Knowledge Distillation | 1 |
| Model Compression | 1 |
| Relation | 1 |
| Representation Learning | 1 |
| model | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections