# HeteroTune: Efficient Federated Learning for Large Heterogeneous Models

arXiv: https://arxiv.org/abs/2411.16796 · HTML: https://mlsanity.com/paper/2411.16796/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 46 references that are in the map.
- First posted on arXiv 25 Nov 2024.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Pre-Trained Image Processing Transformer](https://mlsanity.com/paper/2012.00364/) (2020)
- [Inverting Gradients -- How easy is it to break privacy in federated learning?](https://mlsanity.com/paper/2003.14053/) (2020)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [Pre-trained Models for Natural Language Processing: A Survey](https://mlsanity.com/paper/2003.08271/) (2020)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations](https://mlsanity.com/paper/2409.05976/) (2024)
- [Bilateral Multi-Perspective Matching for Natural Language Sentences](https://mlsanity.com/paper/1702.03814/) (2017)
- [Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models](https://mlsanity.com/paper/2401.06432/) (2024)
- [FedCLIP: Fast Generalization and Personalization for CLIP in Federated Learning](https://mlsanity.com/paper/2302.13485/) (2023)
- [No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices](https://mlsanity.com/paper/2202.08036/) (2022)
- [FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers](https://mlsanity.com/paper/2211.08025/) (2022)
- [FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction](https://mlsanity.com/paper/2407.19389/) (2024)
- [Bridging Model Heterogeneity in Federated Learning via Uncertainty-based Asymmetrical Reciprocity Learning](https://mlsanity.com/paper/2407.03247/) (2024)

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

- [KV Cache Translation across Heterogeneous Large Language Models](https://mlsanity.com/paper/2607.28979/) (2026)
- [UniFed-VLM: Federated Instruction Tuning for Vision-Language Models with Multiple Heterogeneity](https://mlsanity.com/paper/2608.15516/) (2026)

## Abstract (arXiv)

While large pre-trained models have achieved impressive performance across AI tasks, their deployment in privacy-sensitive and distributed environments remains challenging. Federated learning (FL) offers a viable solution by enabling decentralized fine-tuning without data sharing, but real-world applications face significant obstacles due to heterogeneous client resources in compute and memory. To address this, we propose HeteroTune, a novel federated fine-tuning paradigm for large, heterogeneous models operating under limited communication and computation budgets. The core of our method lies in a novel architecture, DeMA (Dense Mixture of Adapters), which enables flexible and efficient aggregation of heterogeneous models by preserving their full representational capacity while facilitating seamless cross-model knowledge fusion. We further introduce CMGA (Cross-Model Gradient Alignment), a lightweight yet effective mechanism that enhances training stability by harmonizing gradient directions across heterogeneous client models during aggregation, mitigating update conflicts and promoting more consistent convergence in federated settings. We provide both theoretical analysis and empirical evidence showing that HeteroTune achieves state-of-the-art performance and efficiency across diverse tasks and model architectures. For example, on LLaMA models, it reduces communication overhead by 99.5%, cuts peak memory usage by ~50%, and improves performance by 4.61%.