Pith. sign in

REVIEW 2 cited by

Speeding up Deep Model Training by Sharing Weights and Then Unsharing

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2110.03848 v1 pith:YRXLVXGI submitted 2021-10-08 cs.LG cs.CL

classification cs.LGcs.CL
keywords trainingbertweightsapproachmodelrepeatedsharingthen
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We propose a simple and efficient approach for training the BERT model. Our approach exploits the special structure of BERT that contains a stack of repeated modules (i.e., transformer encoders). Our proposed approach first trains BERT with the weights shared across all the repeated modules till some point. This is for learning the commonly shared component of weights across all repeated layers. We then stop weight sharing and continue training until convergence. We present theoretic insights for training by sharing weights then unsharing with analysis for simplified models. Empirical experiments on the BERT model show that our method yields better performance of trained models, and significantly reduces the number of training iterations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 2 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Parallel Scaling Law for Language Models

    cs.LG 2025-05 conditional novelty 6.0 of 10

    Running P parallel streams of a language model with learned prefixes gives performance comparable to multiplying parameters by about k log P + 1, with k around 0.33 to 0.39.

  2. A multilevel approach to accelerate the training of Transformers

    cs.LG 2025-04 conditional novelty 5.0 of 10

    A multilevel scheme that alternates fine transformer training with two half-depth coarse models reaches the single-level training loss with 44 percent fewer FLOPs on one small language-model setup.

Pith tools