# Skewness-Guided Pruning of Multimodal Swin Transformers for Federated Skin Lesion Classification on Edge Devices

arXiv: https://arxiv.org/abs/2512.08751 · HTML: https://mlsanity.com/paper/2512.08751/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 38 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [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)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [Model Pruning Enables Efficient Federated Learning on Edge Devices](https://mlsanity.com/paper/1909.12326/) (2019)
- [Chasing Sparsity in Vision Transformers: An End-to-End Exploration](https://mlsanity.com/paper/2106.04533/) (2021)
- [Vision Transformer Pruning](https://mlsanity.com/paper/2104.08500/) (2021)
- [Global Vision Transformer Pruning with Hessian-Aware Saliency](https://mlsanity.com/paper/2110.04869/) (2021)
- [X-Pruner: eXplainable Pruning for Vision Transformers](https://mlsanity.com/paper/2303.04935/) (2023)
- [Pruning Algorithms to Accelerate Convolutional Neural Networks for Edge Applications: A Survey](https://mlsanity.com/paper/2005.04275/) (2020)
- [FedMef: Towards Memory-efficient Federated Dynamic Pruning](https://mlsanity.com/paper/2403.14737/) (2024)
- [Complement Sparsification: Low-Overhead Model Pruning for Federated Learning](https://mlsanity.com/paper/2303.06237/) (2023)
- [Federated Pruning: Improving Neural Network Efficiency with Federated Learning](https://mlsanity.com/paper/2209.06359/) (2022)
- [Model Pruning Enables Localized and Efficient Federated Learning for Yield Forecasting and Data Sharing](https://mlsanity.com/paper/2304.09876/) (2023)
- [Exploring Advances in Transformers and CNN for Skin Lesion Diagnosis on Small Datasets](https://mlsanity.com/paper/2205.15442/) (2022)
- [VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning](https://mlsanity.com/paper/2406.05276/) (2024)
- [Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learning](https://mlsanity.com/paper/2509.00745/) (2025)

## Built on by (most cited first, 1 of 1)

- [EcoFair: Energy-Efficient Inference Routing for Edge AI under Data Degradation](https://mlsanity.com/paper/2603.26483/) (2026)

## Abstract (arXiv)

In recent years, high-performance computer vision models have achieved remarkable success in medical imaging, with some skin lesion classification systems even surpassing dermatology specialists in diagnostic accuracy. However, such models are computationally intensive and large in size, making them unsuitable for deployment on edge devices. In addition, strict privacy constraints hinder centralized data management, motivating the adoption of Federated Learning (FL). To address these challenges, this study proposes a skewness-guided pruning method that selectively prunes the Multi-Head Self-Attention and Multi-Layer Perceptron layers of a multimodal Swin Transformer based on the statistical skewness of their output distributions. The proposed method was validated in a horizontal FL environment and shown to maintain performance while substantially reducing model complexity. Experiments on the compact Swin Transformer demonstrate approximately 36% model size reduction with no loss in accuracy. These findings highlight the feasibility of achieving efficient model compression and privacy-preserving distributed learning for multimodal medical AI on edge devices.