# HAFLQ: Heterogeneous Adaptive Federated LoRA Fine-tuned LLM with Quantization

arXiv: https://arxiv.org/abs/2411.06581 · HTML: https://mlsanity.com/paper/2411.06581/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 37 references that are in the map.
- First posted on arXiv 10 Nov 2024.

## Builds on (most cited first, 24 of 24)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [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)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot](https://mlsanity.com/paper/2301.00774/) (2023)
- [LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale](https://mlsanity.com/paper/2208.07339/) (2022)
- [Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey](https://mlsanity.com/paper/2403.14608/) (2024)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Efficient Intent Detection with Dual Sentence Encoders](https://mlsanity.com/paper/2003.04807/) (2020)
- [A Survey on Model Compression for Large Language Models](https://mlsanity.com/paper/2308.07633/) (2023)
- [Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment](https://mlsanity.com/paper/2312.12148/) (2023)
- [A Survey on Efficient Inference for Large Language Models](https://mlsanity.com/paper/2404.14294/) (2024)
- [Towards Building the Federated GPT: Federated Instruction Tuning](https://mlsanity.com/paper/2305.05644/) (2023)
- [Heterogeneous LoRA for Federated Fine-tuning of On-Device Foundation Models](https://mlsanity.com/paper/2401.06432/) (2024)
- [Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources](https://mlsanity.com/paper/2402.11505/) (2024)
- [PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight Importance](https://mlsanity.com/paper/2206.12562/) (2022)
- [Automated Federated Pipeline for Parameter-Efficient Fine-Tuning of Large Language Models](https://mlsanity.com/paper/2404.06448/) (2024)
- [Promoting Data and Model Privacy in Federated Learning through Quantized LoRA](https://mlsanity.com/paper/2406.10976/) (2024)
- [Device-Edge Cooperative Fine-Tuning of Foundation Models as a 6G Service](https://mlsanity.com/paper/2310.18602/) (2023)
- [Optimal Resource Allocation in Multicast Device-to-Device Communications Underlaying LTE Networks](https://mlsanity.com/paper/1503.03576/) (2015)

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

- [FLoKD: Adaptive Knowledge Distillation for Federated Low-Rank LLM over Wireless Networks](https://mlsanity.com/paper/2609.13580/) (2026)
- [FedFit: Federated Fine-Tuning of LLMs via Vector-Bank Parameterization and Quantization](https://mlsanity.com/paper/2610.01537/) (2026)

## Abstract (arXiv)

Federated fine-tuning of pre-trained Large Language Models (LLMs) enables task-specific adaptation across diverse datasets while preserving privacy. However, challenges such as high computational and memory demands, heterogeneous client resources, bandwidth constraints, and ineffective global aggregation hinder its efficiency. To address these issues, we propose HAFLQ (Heterogeneous Adaptive Federated Low-Rank Adaptation Fine-tuned LLM with Quantization), a novel framework for efficient and scalable federated fine-tuning of LLMs in heterogeneous environments. To reduce memory and computation demands, we propose a salience-driven adaptive LLM quantization framework that evaluates the importance of transformer blocks using a salience metric and applies adaptive block-wise quantization accordingly. To handle heterogeneous computational capabilities, we propose an importance-based parameter truncation and freezing scheme. To address communication bottlenecks, we propose an importance-aware bandwidth-adaptive quantization method, which dynamically adjusts parameter precision based on importance and bandwidth constraints. To improve global model aggregation, we propose an adaptive rank-1 matrix-level aggregation strategy, which prevents information dilution and accelerates convergence by aggregating only updated rank-1 matrices from clients. Experimental results on the text classification task demonstrate that HAFLQ reduces memory usage by 31%, lowers communication cost by 49%, improves accuracy by 50%, and achieves faster convergence compared to the baseline method.