SLaB: Sparse-Lowrank-Binary Decomposition for Efficient Large Language Models

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Li, Ziwei, Ma, Yuang, Kang, Yi
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908939710365696
author Li, Ziwei
Ma, Yuang
Kang, Yi
author_facet Li, Ziwei
Ma, Yuang
Kang, Yi
contents The rapid growth of large language models (LLMs) presents significant deployment challenges due to their massive computational and memory demands. While model compression, such as network pruning, offers potential solutions, most existing methods often fail to maintain good performance at high compression ratios. To address this, we propose SLaB, a novel framework that decomposes each linear layer weight into three complementary components: a sparse matrix, a low-rank matrix, and a binary matrix. SLaB eliminates the need for retraining and leverages activation-aware pruning scores to guide the decomposition process. Experiments on Llama-family models demonstrate that SLaB achieves state-of-the-art performance, reducing perplexity by up to 36% compared to existing methods at 50% compression and improving accuracy by up to 8.98% over the baseline on zero-shot tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2604_04493
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SLaB: Sparse-Lowrank-Binary Decomposition for Efficient Large Language Models
Li, Ziwei
Ma, Yuang
Kang, Yi
Machine Learning
Artificial Intelligence
The rapid growth of large language models (LLMs) presents significant deployment challenges due to their massive computational and memory demands. While model compression, such as network pruning, offers potential solutions, most existing methods often fail to maintain good performance at high compression ratios. To address this, we propose SLaB, a novel framework that decomposes each linear layer weight into three complementary components: a sparse matrix, a low-rank matrix, and a binary matrix. SLaB eliminates the need for retraining and leverages activation-aware pruning scores to guide the decomposition process. Experiments on Llama-family models demonstrate that SLaB achieves state-of-the-art performance, reducing perplexity by up to 36% compared to existing methods at 50% compression and improving accuracy by up to 8.98% over the baseline on zero-shot tasks.
title SLaB: Sparse-Lowrank-Binary Decomposition for Efficient Large Language Models
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2604.04493