paper-with-me

홈 › Papers

Small Contributions, Small Networks: Efficient Neural Network Pruning Based on Relative Importance

2024-10-21 · Mostafa Hussien, Mahmoud Afifi, Kim Khoa Nguyen, Mohamed Cheriet

Recent advancements have scaled neural networks to unprecedented sizes, achieving remarkable performance across a wide range of tasks. However, deploying these large-scale models on resource-constrained devices poses significant challenges due to substantial storage and computational requirements. Neural network pruning has emerged as an effective technique to mitigate these limitations by reducing model size and complexity. In this paper, we introduce an intuitive and interpretable pruning method based on activation statistics, rooted in information theory and statistical analysis. Our approach leverages the statistical properties of neuron activations to identify and remove weights with minimal contributions to neuron outputs. Specifically, we build a distribution of weight contributions across the dataset and utilize its parameters to guide the pruning process. Furthermore, we propose a Pruning-aware Training strategy that incorporates an additional regularization term to enhance the effectiveness of our pruning method. Extensive experiments on multiple datasets and network architectures demonstrate that our method consistently outperforms several baseline and state-of-the-art pruning techniques.

📄 PDF Abstract BibTeX arXiv:2410.16151

Code (0)

등록된 구현이 없습니다.

Tasks

Efficient Neural NetworkNetwork Pruning

Methods 이 논문이 사용한 방법론

Pruning 설명 없음

Similar Papers 제목 키워드 기반

Exploring Weight Importance and Hessian Bias in Model Pruning

2020-06-19 · Mingchen Li, Yahya Sattar, Christos Thrampoulidis, Samet Oymak

Model pruning is an essential procedure for building compact and computationally-efficient machine learning models. A key feature of a good pruning algorithm is that it accurately quantifies the relative importance of th…

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration

2018-11-01 · CVPR 2019 6 · Yang He, Ping Liu, Ziwei Wang, Zhilan Hu 외

Previous works utilized ''smaller-norm-less-important'' criterion to prune filters with smaller norm values in a convolutional neural network. In this paper, we analyze this norm-based criterion and point out that its ef…

image-classificationImage Classification

FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification

2022-07-22 · Xiaofeng Lin, Seungbae Kim, Jungseock Joo

Existing pruning techniques preserve deep neural networks' overall ability to make correct predictions but may also amplify hidden biases during the compression process. We propose a novel pruning method, Fairness-aware …

AttributeFairness

Efficient CNNs via Passive Filter Pruning

2023-04-05 · Arshdeep Singh, Mark D. Plumbley

Convolutional neural networks (CNNs) have shown state-of-the-art performance in various applications. However, CNNs are resource-hungry due to their requirement of high computational complexity and memory storage. Recent…

Computational Efficiencyimage-classificationImage ClassificationScene Classification

CRePE: Convolution-aware Relative Importance in Post-training Pruning with Efficient Search

2026-06-01 · Cheonjun Park arxiv

Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. Post-training pruning (PTP) is an effective approach to reducing these costs by removing weights without additional tr…

Hyperparameter Optimization