Pith. sign in

REVIEW 1 cited by

Enhancing One-shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism

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 2408.10473 v1 pith:AGT45RXU submitted 2024-08-20 cs.CL cs.LG

classification cs.CLcs.LG
keywords pruningprunedlanguagemodelone-shotperformanceplmsconnections
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Pre-trained language models (PLMs) are engineered to be robust in contextual understanding and exhibit outstanding performance in various natural language processing tasks. However, their considerable size incurs significant computational and storage costs. Modern pruning strategies employ one-shot techniques to compress PLMs without the need for retraining on task-specific or otherwise general data; however, these approaches often lead to an indispensable reduction in performance. In this paper, we propose SDS, a Sparse-Dense-Sparse pruning framework to enhance the performance of the pruned PLMs from a weight distribution optimization perspective. We outline the pruning process in three steps. Initially, we prune less critical connections in the model using conventional one-shot pruning methods. Next, we reconstruct a dense model featuring a pruning-friendly weight distribution by reactivating pruned connections with sparse regularization. Finally, we perform a second pruning round, yielding a superior pruned model compared to the initial pruning. Experimental results demonstrate that SDS outperforms the state-of-the-art pruning techniques SparseGPT and Wanda under an identical sparsity configuration. For instance, SDS reduces perplexity by 9.13 on Raw-Wikitext2 and improves accuracy by an average of 2.05% across multiple zero-shot benchmarks for OPT-125M with 2:4 sparsity.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Pivoting Factorization: A Compact Meta Low-Rank Representation of Sparsity for Efficient Inference in Large Language Models

    cs.LG 2025-01 conditional novelty 4.0 of 10

    A low-rank LLM compression method that stores a row basis of each weight matrix plus coefficients, together with an online error-minimizing reconstruction, reports perplexity near 2:4 semi-structured pruning with bett...

Pith tools