# Automatic Channel Pruning for Multi-Head Attention

arXiv: https://arxiv.org/abs/2405.20867 · HTML: https://mlsanity.com/paper/2405.20867/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 45 references that are in the map.
- First posted on arXiv 31 May 2024.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Reformer: The Efficient Transformer](https://mlsanity.com/paper/2001.04451/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet](https://mlsanity.com/paper/2101.11986/) (2021)
- [Token Merging: Your ViT But Faster](https://mlsanity.com/paper/2210.09461/) (2022)
- [CvT: Introducing Convolutions to Vision Transformers](https://mlsanity.com/paper/2103.15808/) (2021)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [ConViT: Improving Vision Transformers with Soft Convolutional Inductive Biases](https://mlsanity.com/paper/2103.10697/) (2021)
- [Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations](https://mlsanity.com/paper/2202.07800/) (2022)
- [CMT: Convolutional Neural Networks Meet Vision Transformers](https://mlsanity.com/paper/2107.06263/) (2021)
- [Vision Transformer with Deformable Attention](https://mlsanity.com/paper/2201.00520/) (2022)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [Neighborhood Attention Transformer](https://mlsanity.com/paper/2204.07143/) (2022)
- [MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning](https://mlsanity.com/paper/1903.10258/) (2019)
- [cosFormer: Rethinking Softmax in Attention](https://mlsanity.com/paper/2202.08791/) (2022)
- [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021)
- [FLatten Transformer: Vision Transformer using Focused Linear Attention](https://mlsanity.com/paper/2308.00442/) (2023)
- [SOFT: Softmax-free Transformer with Linear Complexity](https://mlsanity.com/paper/2110.11945/) (2021)
- [EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications](https://mlsanity.com/paper/2206.10589/) (2022)
- [Joint Token Pruning and Squeezing Towards More Aggressive Compression of Vision Transformers](https://mlsanity.com/paper/2304.10716/) (2023)
- [Vision Transformer Pruning](https://mlsanity.com/paper/2104.08500/) (2021)
- [Unified Visual Transformer Compression](https://mlsanity.com/paper/2203.08243/) (2022)
- [Global Vision Transformer Pruning with Hessian-Aware Saliency](https://mlsanity.com/paper/2110.04869/) (2021)
- [SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications](https://mlsanity.com/paper/2303.15446/) (2023)

## Built on by (most cited first, 3 of 3)

- [Supervised Fine-Tuning Achieve Rapid Task Adaption Via Alternating Attention Head Activation Patterns](https://mlsanity.com/paper/2409.15820/) (2024)
- [HEART-VIT: Hessian-Guided Efficient Dynamic Attention and Token Pruning in Vision Transformer](https://mlsanity.com/paper/2512.20120/) (2025)
- [Performance-Efficiency Tradeoffs in Transformers: An Approximation Theory Perspective](https://mlsanity.com/paper/2510.03784/) (2025)

## Abstract (arXiv)

Despite the strong performance of Transformers, their quadratic computation complexity presents challenges in applying them to vision tasks. Automatic pruning is one of effective methods for reducing computation complexity without heuristic approaches. However, directly applying it to multi-head attention is not straightforward due to channel misalignment. In this paper, we propose an automatic channel pruning method to take into account the multi-head attention mechanism. First, we incorporate channel similarity-based weights into the pruning indicator to preserve more informative channels in each head. Then, we adjust pruning indicator to enforce removal of channels in equal proportions across all heads, preventing the channel misalignment. We also add a reweight module to compensate for information loss resulting from channel removal, and an effective initialization step for pruning indicator based on difference of attention between original structure and each channel. Our proposed method can be used to not only original attention, but also linear attention, which is more efficient as linear complexity with respect to the number of tokens. On ImageNet-1K, applying our pruning method to the FLattenTransformer, which includes both attention mechanisms, shows outperformed accuracy for several MACs compared with previous state-of-the-art efficient models and pruned methods. Code will be available soon.