# Efficient Federated Finetuning of Tiny Transformers with Resource-Constrained Devices

arXiv: https://arxiv.org/abs/2411.07826 · HTML: https://mlsanity.com/paper/2411.07826/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 33 references that are in the map.
- First posted on arXiv 12 Nov 2024.

## Builds on (most cited first, 21 of 21)

- [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)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [GIT: A Generative Image-to-text Transformer for Vision and Language](https://mlsanity.com/paper/2205.14100/) (2022)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [UniT: Multimodal Multitask Learning with a Unified Transformer](https://mlsanity.com/paper/2102.10772/) (2021)
- [FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout](https://mlsanity.com/paper/2102.13451/) (2021)
- [FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare](https://mlsanity.com/paper/1907.09173/) (2019)
- [Expanding the Reach of Federated Learning by Reducing Client Resource Requirements](https://mlsanity.com/paper/1812.07210/) (2018)
- [Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models](https://mlsanity.com/paper/2401.06432/) (2024)
- [FedRolex: Model-Heterogeneous Federated Learning with Rolling Sub-Model Extraction](https://mlsanity.com/paper/2212.01548/) (2022)
- [SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models](https://mlsanity.com/paper/2308.06522/) (2023)
- [Federated Learning for Computationally-Constrained Heterogeneous Devices: A Survey](https://mlsanity.com/paper/2307.09182/) (2023)
- [FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization](https://mlsanity.com/paper/2111.14655/) (2021)
- [ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training](https://mlsanity.com/paper/2110.05323/) (2021)
- [A Federated Learning Framework for Healthcare IoT devices](https://mlsanity.com/paper/2005.05083/) (2020)
- [Heterogeneous Federated Learning](https://mlsanity.com/paper/2008.06767/) (2020)
- [Federated Learning for Localization: A Privacy-Preserving Crowdsourcing Method](https://mlsanity.com/paper/2001.01911/) (2020)
- [CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantization](https://mlsanity.com/paper/2203.05468/) (2022)
- [Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices](https://mlsanity.com/paper/2305.17005/) (2023)

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

- [Integration of TinyML and LargeML: A Survey of 6G and Beyond](https://mlsanity.com/paper/2505.15854/) (2025)

## Abstract (arXiv)

In recent years, Large Language Models (LLMs) through Transformer structures have dominated many machine learning tasks, especially text processing. However, these models require massive amounts of data for training and induce high resource requirements, particularly in terms of the large number of Floating Point Operations (FLOPs) and the high amounts of memory needed. To fine-tune such a model in a parameter-efficient way, techniques like Adapter or LoRA have been developed. However, we observe that the application of LoRA, when used in federated learning (FL), while still being parameter-efficient, is memory and FLOP inefficient. Based on that observation, we develop a novel layer finetuning scheme that allows devices in cross-device FL to make use of pretrained neural networks (NNs) while adhering to given resource constraints. We show that our presented scheme outperforms the current state of the art when dealing with homogeneous or heterogeneous computation and memory constraints and is on par with LoRA regarding limited communication, thereby achieving significantly higher accuracies in FL training.