Iterative Activation-based Structured Pruning
Deploying complex deep learning models on edge devices is challenging because they have substantial compute and memory resource requirements, whereas edge devices' resource budget is limited. To solve this problem, extensive pruning techniques have been proposed for compressing networks. Recent advances based on the Lottery Ticket Hypothesis (LTH) show that iterative model pruning tends to produce smaller and more accurate models. However, LTH research focuses on unstructured pruning, which is hardware-inefficient and difficult to accelerate on hardware platforms. In this paper, we investigate iterative pruning in the context of structured pruning because structurally pruned models map well on commodity hardware. We find that directly applying a structured weight-based pruning technique iteratively, called iterative L1-norm based pruning (ILP), does not produce accurate pruned models. To solve this problem, we propose two activation-based pruning methods, Iterative Activation-based Pruning (IAP) and Adaptive Iterative Activation-based Pruning (AIAP). We observe that, with only 1% accuracy loss, IAP and AIAP achieve 7.75X and 15.88$X compression on LeNet-5, and 1.25X and 1.71X compression on ResNet-50, whereas ILP achieves 4.77X and 1.13X, respectively.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adaptive Activation-based Structured Pruning
Pruning is a promising approach to compress complex deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yie…
Pruning Large Language Models to Intra-module Low-rank Architecture with Transitional Activations
Structured pruning fundamentally reduces computational and memory overheads of large language models (LLMs) and offers a feasible solution for end-side LLM deployment. Structurally pruned models remain dense and high-pre…
Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions
Pruning is a promising approach to compress deep learning models in order to deploy them on resource-constrained edge devices. However, many existing pruning solutions are based on unstructured pruning, which yields mode…
i-SpaSP: Structured Neural Pruning via Sparse Signal Recovery
We propose a novel, structured pruning algorithm for neural networks -- the iterative, Sparse Structured Pruning algorithm, dubbed as i-SpaSP. Inspired by ideas from sparse signal recovery, i-SpaSP operates by iterativel…
CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation Information
The colossal parameters and computational overhead of Large Language Models (LLMs) challenge their real-world applications. Network pruning, which targets unstructured or structured sparsity by removing redundant paramet…
Network Pruning