# FGFP: A Fractional Gaussian Filter and Pruning for Deep Neural Networks Compression

arXiv: https://arxiv.org/abs/2507.22527 · HTML: https://mlsanity.com/paper/2507.22527/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation](https://mlsanity.com/paper/1404.0736/) (2014)
- [A Systematic DNN Weight Pruning Framework using Alternating Direction Method of Multipliers](https://mlsanity.com/paper/1804.03294/) (2018)
- [SCOP: Scientific Control for Reliable Neural Network Pruning](https://mlsanity.com/paper/2010.10732/) (2020)
- [Stable Low-rank Tensor Decomposition for Compression of Convolutional Neural Network](https://mlsanity.com/paper/2008.05441/) (2020)
- [Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression](https://mlsanity.com/paper/2003.08935/) (2020)
- [Towards Compact CNNs via Collaborative Compression](https://mlsanity.com/paper/2105.11228/) (2021)
- [Efficient Neural Network Training via Forward and Backward Propagation Sparsification](https://mlsanity.com/paper/2111.05685/) (2021)
- [Growing Efficient Deep Networks by Structured Continuous Sparsification](https://mlsanity.com/paper/2007.15353/) (2020)
- [Heuristic Rank Selection with Progressively Searching Tensor Ring Network](https://mlsanity.com/paper/2009.10580/) (2020)
- [Low-rank Tensor Decomposition for Compression of Convolutional Neural Networks Using Funnel Regularization](https://mlsanity.com/paper/2112.03690/) (2021)
- [Compact Model Training by Low-Rank Projection with Energy Transfer](https://mlsanity.com/paper/2204.05566/) (2022)

## Abstract (arXiv)

Network compression techniques have become increasingly important in recent years because the loads of Deep Neural Networks (DNNs) are heavy for edge devices in real-world applications. While many methods compress neural network parameters, deploying these models on edge devices remains challenging. To address this, we propose the fractional Gaussian filter and pruning (FGFP) framework, which integrates fractional-order differential calculus and Gaussian function to construct fractional Gaussian filters (FGFs). To reduce the computational complexity of fractional-order differential operations, we introduce Gr"unwald-Letnikov fractional derivatives to approximate the fractional-order differential equation. The number of parameters for each kernel in FGF is minimized to only seven. Beyond the architecture of Fractional Gaussian Filters, our FGFP framework also incorporates Adaptive Unstructured Pruning (AUP) to achieve higher compression ratios. Experiments on various architectures and benchmarks show that our FGFP framework outperforms recent methods in accuracy and compression. On CIFAR-10, ResNet-20 achieves only a 1.52% drop in accuracy while reducing the model size by 85.2%. On ImageNet2012, ResNet-50 achieves only a 1.63% drop in accuracy while reducing the model size by 69.1%.