# Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers

arXiv: https://arxiv.org/abs/1802.00124 · HTML: https://mlsanity.com/paper/1802.00124/

## Key facts

- Cited by 112 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2018.

## Built on by (most cited first, 30 of 112)

- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Structural Pruning for Diffusion Models](https://mlsanity.com/paper/2305.10924/) (2023)
- [Patch Slimming for Efficient Vision Transformers](https://mlsanity.com/paper/2106.02852/) (2021)
- [Group Fisher Pruning for Practical Network Compression](https://mlsanity.com/paper/2108.00708/) (2021)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space](https://mlsanity.com/paper/2201.00814/) (2022)
- [Revisiting Random Channel Pruning for Neural Network Compression](https://mlsanity.com/paper/2205.05676/) (2022)
- [Low-rank lottery tickets: finding efficient low-rank neural networks via matrix differential equations](https://mlsanity.com/paper/2205.13571/) (2022)
- [Accelerating Large Scale Real-Time GNN Inference using Channel Pruning](https://mlsanity.com/paper/2105.04528/) (2021)
- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [CHEX: CHannel EXploration for CNN Model Compression](https://mlsanity.com/paper/2203.15794/) (2022)
- [Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety](https://mlsanity.com/paper/2104.14235/) (2021)
- [Domain Generalization through Audio-Visual Relative Norm Alignment in First Person Action Recognition](https://mlsanity.com/paper/2110.10101/) (2021)
- [Single Image Depth Prediction with Wavelet Decomposition](https://mlsanity.com/paper/2106.02022/) (2021)
- [Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition](https://mlsanity.com/paper/2107.11442/) (2021)
- [GDP: Stabilized Neural Network Pruning via Gates with Differentiable Polarization](https://mlsanity.com/paper/2109.02220/) (2021)
- [Content-Aware GAN Compression](https://mlsanity.com/paper/2104.02244/) (2021)
- [Dual Lottery Ticket Hypothesis](https://mlsanity.com/paper/2203.04248/) (2022)
- [Network Pruning That Matters: A Case Study on Retraining Variants](https://mlsanity.com/paper/2105.03193/) (2021)
- [Optimal ablation for interpretability](https://mlsanity.com/paper/2409.09951/) (2024)
- [Denoising Diffusion Step-aware Models](https://mlsanity.com/paper/2310.03337/) (2023)
- [Isomorphic Pruning for Vision Models](https://mlsanity.com/paper/2407.04616/) (2024)
- [Pruning Neural Networks via Coresets and Convex Geometry: Towards No Assumptions](https://mlsanity.com/paper/2209.08554/) (2022)
- [A Unified Approach to Coreset Learning](https://mlsanity.com/paper/2111.03044/) (2021)
- [Improving Knowledge Distillation via Regularizing Feature Norm and Direction](https://mlsanity.com/paper/2305.17007/) (2023)
- [Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters](https://mlsanity.com/paper/2202.07190/) (2022)
- [Trainability Preserving Neural Pruning](https://mlsanity.com/paper/2207.12534/) (2022)
- [MMR-Mamba: Multi-Modal MRI Reconstruction with Mamba and Spatial-Frequency Information Fusion](https://mlsanity.com/paper/2406.18950/) (2024)
- [Provable and Efficient Continual Representation Learning](https://mlsanity.com/paper/2203.02026/) (2022)

## Abstract (arXiv)

Model pruning has become a useful technique that improves the computational efficiency of deep learning, making it possible to deploy solutions in resource-limited scenarios. A widely-used practice in relevant work assumes that a smaller-norm parameter or feature plays a less informative role at the inference time. In this paper, we propose a channel pruning technique for accelerating the computations of deep convolutional neural networks (CNNs) that does not critically rely on this assumption. Instead, it focuses on direct simplification of the channel-to-channel computation graph of a CNN without the need of performing a computationally difficult and not-always-useful task of making high-dimensional tensors of CNN structured sparse. Our approach takes two stages: first to adopt an end-to- end stochastic training method that eventually forces the outputs of some channels to be constant, and then to prune those constant channels from the original neural network by adjusting the biases of their impacting layers such that the resulting compact model can be quickly fine-tuned. Our approach is mathematically appealing from an optimization perspective and easy to reproduce. We experimented our approach through several image learning benchmarks and demonstrate its interesting aspects and competitive performance.