# Class-Aware Pruning for Efficient Neural Networks

arXiv: https://arxiv.org/abs/2312.05875 · HTML: https://mlsanity.com/paper/2312.05875/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 28 references that are in the map.
- First posted on arXiv 10 Dec 2023.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Learning Sparse Neural Networks through L0 Regularization](https://mlsanity.com/paper/1712.01312/) (2017)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [BlockDrop: Dynamic Inference Paths in Residual Networks](https://mlsanity.com/paper/1711.08393/) (2017)
- [Data-Driven Sparse Structure Selection for Deep Neural Networks](https://mlsanity.com/paper/1707.01213/) (2017)
- [Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks](https://mlsanity.com/paper/1909.08174/) (2019)
- [CHIP: CHannel Independence-based Pruning for Compact Neural Networks](https://mlsanity.com/paper/2110.13981/) (2021)
- [Operation-Aware Soft Channel Pruning using Differentiable Masks](https://mlsanity.com/paper/2007.03938/) (2020)
- [Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradients](https://mlsanity.com/paper/2202.08132/) (2022)
- [Neural Response Interpretation through the Lens of Critical Pathways](https://mlsanity.com/paper/2103.16886/) (2021)
- [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)

## Built on by (most cited first, 9 of 9)

- [Basis Sharing: Cross-Layer Parameter Sharing for Large Language Model Compression](https://mlsanity.com/paper/2410.03765/) (2024)
- [LiveMind: Low-latency Large Language Models with Simultaneous Inference](https://mlsanity.com/paper/2406.14319/) (2024)
- [Enhanced Pruning Strategy for Multi-Component Neural Architectures Using Component-Aware Graph Analysis](https://mlsanity.com/paper/2504.13296/) (2025)
- [EncodingNet: A Novel Encoding-based MAC Design for Efficient Neural Network Acceleration](https://mlsanity.com/paper/2402.18595/) (2024)
- [COMponent-Aware Pruning for Accelerated Control Tasks in Latent Space Models](https://mlsanity.com/paper/2508.08144/) (2025)
- [Layer-wise Weight Selection for Power-Efficient Neural Network Acceleration](https://mlsanity.com/paper/2511.17123/) (2025)
- [Late Breaking Results: Conversion of Neural Networks into Logic Flows for Edge Computing](https://mlsanity.com/paper/2601.22151/) (2026)
- [DANCE: Dynamic 3D CNN Pruning: Joint Frame, Channel, and Feature Adaptation for Energy Efficiency on the Edge](https://mlsanity.com/paper/2603.17275/) (2026)
- [DiffLUT-Net: Differentiable Training of FPGA LUT Networks with Learnable Connectivity](https://mlsanity.com/paper/2609.09254/) (2026)

## Abstract (arXiv)

Deep neural networks (DNNs) have demonstrated remarkable success in various fields. However, the large number of floating-point operations (FLOPs) in DNNs poses challenges for their deployment in resource-constrained applications, e.g., edge devices. To address the problem, pruning has been introduced to reduce the computational cost in executing DNNs. Previous pruning strategies are based on weight values, gradient values and activation outputs. Different from previous pruning solutions, in this paper, we propose a class-aware pruning technique to compress DNNs, which provides a novel perspective to reduce the computational cost of DNNs. In each iteration, the neural network training is modified to facilitate the class-aware pruning. Afterwards, the importance of filters with respect to the number of classes is evaluated. The filters that are only important for a few number of classes are removed. The neural network is then retrained to compensate for the incurred accuracy loss. The pruning iterations end until no filter can be removed anymore, indicating that the remaining filters are very important for many classes. This pruning technique outperforms previous pruning solutions in terms of accuracy, pruning ratio and the reduction of FLOPs. Experimental results confirm that this class-aware pruning technique can significantly reduce the number of weights and FLOPs, while maintaining a high inference accuracy.