LLM-QFL: Distilling Large Language Model for Quantum Federated Learning

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gurung, Dev, Pokhrel, Shiva Raj
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909622115237888
author Gurung, Dev
Pokhrel, Shiva Raj
author_facet Gurung, Dev
Pokhrel, Shiva Raj
contents Inspired by the power of large language models (LLMs), our research adapts them to quantum federated learning (QFL) to boost efficiency and performance. We propose a federated fine-tuning method that distills an LLM within QFL, allowing each client to locally adapt the model to its own data while preserving privacy and reducing unnecessary global updates. The fine-tuned LLM also acts as a reinforcement agent, optimizing QFL by adjusting optimizer steps, cutting down communication rounds, and intelligently selecting clients. Experiments show significant efficiency gains. We pioneer a synergy between LLM and QFL, offering: i) practical efficiency: Reduced communication costs and faster convergence. ii) theoretical rigor: Provable guarantees for adaptive federated optimization. iii) scalability: PEFT methods (LoRA, QLoRA) enable deployment on resource-constrained quantum devices. Code implementation is available here 1.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18656
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-QFL: Distilling Large Language Model for Quantum Federated Learning
Gurung, Dev
Pokhrel, Shiva Raj
Machine Learning
Inspired by the power of large language models (LLMs), our research adapts them to quantum federated learning (QFL) to boost efficiency and performance. We propose a federated fine-tuning method that distills an LLM within QFL, allowing each client to locally adapt the model to its own data while preserving privacy and reducing unnecessary global updates. The fine-tuned LLM also acts as a reinforcement agent, optimizing QFL by adjusting optimizer steps, cutting down communication rounds, and intelligently selecting clients. Experiments show significant efficiency gains. We pioneer a synergy between LLM and QFL, offering: i) practical efficiency: Reduced communication costs and faster convergence. ii) theoretical rigor: Provable guarantees for adaptive federated optimization. iii) scalability: PEFT methods (LoRA, QLoRA) enable deployment on resource-constrained quantum devices. Code implementation is available here 1.
title LLM-QFL: Distilling Large Language Model for Quantum Federated Learning
topic Machine Learning
url https://arxiv.org/abs/2505.18656