Electrostatic Force Regularization for Neural Structured Pruning Article Swipe

MAKE IMPACT

Abdesselam Ferdi , Abdelmalik Taleb‐Ahmed , Amir Nakib , Youcef Ferdi · YOU? · · 2024 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2411.11079

The demand for deploying deep convolutional neural networks (DCNNs) on resource-constrained devices for real-time applications remains substantial. However, existing state-of-the-art structured pruning methods often involve intricate implementations, require modifications to the original network architectures, and necessitate an extensive fine-tuning phase. To overcome these challenges, we propose a novel method that, for the first time, incorporates the concepts of charge and electrostatic force from physics into the training process of DCNNs. The magnitude of this force is directly proportional to the product of the charges of the convolution filter and the source filter, and inversely proportional to the square of the distance between them. We applied this electrostatic-like force to the convolution filters, either attracting filters with opposite charges toward non-zero weights or repelling filters with like charges toward zero weights. Consequently, filters subject to repulsive forces have their weights reduced to zero, enabling their removal, while the attractive forces preserve filters with significant weights that retain information. Unlike conventional methods, our approach is straightforward to implement, does not require any architectural modifications, and simultaneously optimizes weights and ranks filter importance, all without the need for extensive fine-tuning. We validated the efficacy of our method on modern DCNN architectures using the MNIST, CIFAR, and ImageNet datasets, achieving competitive performance compared to existing structured pruning approaches.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2411.11079

PDF

https://arxiv.org/pdf/2411.11079

OA Status

green

Cited By

1

Related Works

10

OpenAlex ID

https://openalex.org/W4404570552

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4404570552

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2411.11079

Digital Object Identifier

Title

Electrostatic Force Regularization for Neural Structured Pruning

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2024

Year of publication

Publication date

2024-11-17

Full publication date if available

Authors

Abdesselam Ferdi, Abdelmalik Taleb‐Ahmed, Amir Nakib, Youcef Ferdi

List of authors in order

Landing page

https://arxiv.org/abs/2411.11079

Publisher landing page

PDF URL

https://arxiv.org/pdf/2411.11079

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2411.11079

Direct OA link when available

Concepts

Regularization (linguistics), Pruning, Artificial neural network, Artificial intelligence, Computer science, Mathematics, Biological system, Biology, Botany

Top concepts (fields/topics) attached by OpenAlex

Cited by

1

Total citation count in OpenAlex

Citations by year (recent)

2025: 1

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload