# CoSeP: Complementary Separability Pruning via Class-Separability Clustering

arXiv: https://arxiv.org/abs/2505.13225 · HTML: https://mlsanity.com/paper/2505.13225/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 48 references that are in the map.
- First posted on arXiv 19 May 2025.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [What is the State of Neural Network Pruning?](https://mlsanity.com/paper/2003.03033/) (2020)
- [ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression](https://mlsanity.com/paper/1707.06342/) (2017)
- [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018)
- [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019)
- [DepGraph: Towards Any Structural Pruning](https://mlsanity.com/paper/2301.12900/) (2023)
- [Discrimination-aware Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/1810.11809/) (2018)
- [Structured Pruning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.08571/) (2015)
- [Structured Pruning for Deep Convolutional Neural Networks: A survey](https://mlsanity.com/paper/2303.00566/) (2023)
- [SCOP: Scientific Control for Reliable Neural Network Pruning](https://mlsanity.com/paper/2010.10732/) (2020)
- [Channel Pruning via Automatic Structure Search](https://mlsanity.com/paper/2001.08565/) (2020)
- [CHIP: CHannel Independence-based Pruning for Compact Neural Networks](https://mlsanity.com/paper/2110.13981/) (2021)
- [Faster k-Medoids Clustering: Improving the PAM, CLARA, and CLARANS Algorithms](https://mlsanity.com/paper/1810.05691/) (2018)
- [Towards Compact CNNs via Collaborative Compression](https://mlsanity.com/paper/2105.11228/) (2021)
- [DECORE: Deep Compression with Reinforcement Learning](https://mlsanity.com/paper/2106.06091/) (2021)
- [Auto-Train-Once: Controller Network Guided Automatic Network Pruning from Scratch](https://mlsanity.com/paper/2403.14729/) (2024)
- [Soft Masking for Cost-Constrained Channel Pruning](https://mlsanity.com/paper/2211.02206/) (2022)
- [Automatic Attention Pruning: Improving and Automating Model Pruning using Attentions](https://mlsanity.com/paper/2303.08595/) (2023)
- [Effective Layer Pruning Through Similarity Metric Perspective](https://mlsanity.com/paper/2405.17081/) (2024)
- [REPrune: Channel Pruning via Kernel Representative Selection](https://mlsanity.com/paper/2402.17862/) (2024)
- [Graph-Based Automatic Feature Selection for Multi-Class Classification via Mean Simplified Silhouette](https://mlsanity.com/paper/2309.02272/) (2023)
- [Electrostatic Force Regularization for Neural Structured Pruning](https://mlsanity.com/paper/2411.11079/) (2024)
- [SNF: Filter Pruning via Searching the Proper Number of Filters](https://mlsanity.com/paper/2112.07282/) (2021)

## Abstract (arXiv)

Neural network pruning aims to compress models for efficient deployment, yet two fundamental challenges remain. First, many methods rely on per-component importance scores, selecting filters or neurons independently and ignoring redundancy: the retained set may include multiple components capturing similar discriminative patterns while missing others entirely. Second, determining per-layer pruning ratios typically requires manual, architecture-specific tuning with no principled stopping criterion. We propose CoSeP (Complementary Separability Pruning) to address both issues. Rather than scoring components in isolation, CoSeP represents each component by its class-separability profile across all class pairs, computed via Jeffries--Matusita distances. This defines a separability space in which nearby components are potentially redundant and distant components capture complementary information. CoSeP selects a compact set of representatives in this space: components are grouped via k-medoids clustering, candidate subset sizes are evaluated using the Mean Simplified Silhouette, and a knee-detection criterion automatically determines how many components to retain. Across CIFAR-10, CIFAR-100, and ImageNet-1K, on ResNet, VGG, MobileNet, and DenseNet architectures, CoSeP matches or improves accuracy while reducing FLOPs, with measured wall-clock inference-time reductions of up to 20%. For example, it achieves a +0.66% top-1 accuracy gain with 2.30x FLOPs reduction on ResNet-50/ImageNet-1K, and a 0.37% gain with 2.59x FLOPs reduction on VGG-16/CIFAR-10. These results demonstrate that modeling complementarity in class-separability space provides an effective and principled approach to pruning.