A Sparsity Predicting Approach for Large Language Models via Activation Pattern Clustering

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dhar, Nobel, Deng, Bobin, Islam, Md Romyull, Zhang, Xinyue, Nasif, Kazi Fahim Ahmad, Suo, Kun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915398288408576
author Dhar, Nobel
Deng, Bobin
Islam, Md Romyull
Zhang, Xinyue
Nasif, Kazi Fahim Ahmad
Suo, Kun
author_facet Dhar, Nobel
Deng, Bobin
Islam, Md Romyull
Zhang, Xinyue
Nasif, Kazi Fahim Ahmad
Suo, Kun
contents Large Language Models (LLMs) exhibit significant activation sparsity, where only a subset of neurons are active for a given input. Although this sparsity presents opportunities to reduce computational cost, efficiently utilizing it requires predicting activation patterns in a scalable manner. However, direct prediction at the neuron level is computationally expensive due to the vast number of neurons in modern LLMs. To enable efficient prediction and utilization of activation sparsity, we propose a clustering-based activation pattern compression framework. Instead of treating each neuron independently, we group similar activation patterns into a small set of representative clusters. Our method achieves up to 79.34% clustering precision, outperforming standard binary clustering approaches while maintaining minimal degradation in perplexity (PPL) scores. With a sufficiently large number of clusters, our approach attains a PPL score as low as 12.49, demonstrating its effectiveness in preserving model quality while reducing computational overhead. By predicting cluster assignments rather than individual neuron states, future models can efficiently infer activation patterns from pre-computed centroids. We detail the clustering algorithm, analyze its effectiveness in capturing meaningful activation structures, and demonstrate its potential to improve sparse computation efficiency. This clustering-based formulation serves as a foundation for future work on activation pattern prediction, paving the way for efficient inference in large-scale language models.
format Preprint
id arxiv_https___arxiv_org_abs_2507_14179
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Sparsity Predicting Approach for Large Language Models via Activation Pattern Clustering
Dhar, Nobel
Deng, Bobin
Islam, Md Romyull
Zhang, Xinyue
Nasif, Kazi Fahim Ahmad
Suo, Kun
Machine Learning
Artificial Intelligence
Computation and Language
Distributed, Parallel, and Cluster Computing
Large Language Models (LLMs) exhibit significant activation sparsity, where only a subset of neurons are active for a given input. Although this sparsity presents opportunities to reduce computational cost, efficiently utilizing it requires predicting activation patterns in a scalable manner. However, direct prediction at the neuron level is computationally expensive due to the vast number of neurons in modern LLMs. To enable efficient prediction and utilization of activation sparsity, we propose a clustering-based activation pattern compression framework. Instead of treating each neuron independently, we group similar activation patterns into a small set of representative clusters. Our method achieves up to 79.34% clustering precision, outperforming standard binary clustering approaches while maintaining minimal degradation in perplexity (PPL) scores. With a sufficiently large number of clusters, our approach attains a PPL score as low as 12.49, demonstrating its effectiveness in preserving model quality while reducing computational overhead. By predicting cluster assignments rather than individual neuron states, future models can efficiently infer activation patterns from pre-computed centroids. We detail the clustering algorithm, analyze its effectiveness in capturing meaningful activation structures, and demonstrate its potential to improve sparse computation efficiency. This clustering-based formulation serves as a foundation for future work on activation pattern prediction, paving the way for efficient inference in large-scale language models.
title A Sparsity Predicting Approach for Large Language Models via Activation Pattern Clustering
topic Machine Learning
Artificial Intelligence
Computation and Language
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2507.14179