# EFTViT: Efficient Federated Training of Vision Transformers with Masked Images on Resource-Constrained Clients

arXiv: https://arxiv.org/abs/2412.00334 · HTML: https://mlsanity.com/paper/2412.00334/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 30 Nov 2024.

## Builds on (most cited first, 26 of 26)

- [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)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers](https://mlsanity.com/paper/2012.15840/) (2020)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Deep Leakage from Gradients](https://mlsanity.com/paper/1906.08935/) (2019)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [iDLG: Improved Deep Leakage from Gradients](https://mlsanity.com/paper/2001.02610/) (2020)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [See through Gradients: Image Batch Recovery via GradInversion](https://mlsanity.com/paper/2104.07586/) (2021)
- [Revealing the Dark Secrets of Masked Image Modeling](https://mlsanity.com/paper/2205.13543/) (2022)
- [FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction](https://mlsanity.com/paper/2212.01548/) (2022)
- [When Federated Learning Meets Pre-trained Language Models' Parameter-Efficient Tuning Methods](https://mlsanity.com/paper/2212.10025/) (2022)
- [DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers](https://mlsanity.com/paper/2204.12997/) (2022)
- [Instant3D: Instant Text-to-3D Generation](https://mlsanity.com/paper/2311.08403/) (2023)
- [STPrivacy: Spatio-Temporal Privacy-Preserving Action Recognition](https://mlsanity.com/paper/2301.03046/) (2023)
- [Self-supervised Geometric Features Discovery via Interpretable Attention for Vehicle Re-Identification and Beyond](https://mlsanity.com/paper/2010.09221/) (2020)
- [FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients](https://mlsanity.com/paper/2311.11227/) (2023)
- [RealEra: Semantic-level Concept Erasure via Neighbor-Concept Mining](https://mlsanity.com/paper/2410.09140/) (2024)
- [AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems](https://mlsanity.com/paper/2311.13166/) (2023)

## Built on by (most cited first, 2 of 2)

- [SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding](https://mlsanity.com/paper/2505.17674/) (2025)
- [DeepAFL: Deep Analytic Federated Learning](https://mlsanity.com/paper/2603.00579/) (2026)

## Abstract (arXiv)

Federated learning research has recently shifted from Convolutional Neural Networks (CNNs) to Vision Transformers (ViTs) due to their superior capacity. ViTs training demands higher computational resources due to the lack of 2D inductive biases inherent in CNNs. However, efficient federated training of ViTs on resource-constrained edge devices remains unexplored in the community. In this paper, we propose EFTViT, a hierarchical federated framework that leverages masked images to enable efficient, full-parameter training on resource-constrained edge devices, offering substantial benefits for learning on heterogeneous data. In general, we patchify images and randomly mask a portion of the patches, observing that excluding them from training has minimal impact on performance while substantially reducing computation costs and enhancing data content privacy protection. Specifically, EFTViT comprises a series of lightweight local modules and a larger global module, updated independently on clients and the central server, respectively. The local modules are trained on masked image patches, while the global module is trained on intermediate patch features uploaded from the local client, balanced through a proposed median sampling strategy to erase client data distribution privacy. We analyze the computational complexity and privacy protection of EFTViT. Extensive experiments on popular benchmarks show that EFTViT achieves up to 28.17% accuracy improvement, reduces local training computational cost by up to 2.8×, and cuts local training time by up to 4.4× compared to existing methods.