Quantum-Enhanced LLM Efficient Fine Tuning

• URL: http://arxiv.org/abs/2503.12790v2
• Date: Sun, 27 Apr 2025 10:23:02 GMT
• Title: Quantum-Enhanced LLM Efficient Fine Tuning
• Authors: Xiaofei Kong, Lei Li, Zhaoyun Chen, Cheng Xue, Xiaofan Xu, Huanyu Liu, Yuchun Wu, Yuan Fang, Han Fang, Kejiang Chen, Yang Yang, Menghan Dou, Guoping Guo,
• Abstract summary: Low-Rank Adaptation (LoRA) enables efficient fine-tuning of pre-trained language models through low-rank matrix approximation.<n>We propose Quantum Hybrid Adaptation (QTHA), a parameter-efficient fine-tuning method that integrates a quantum neural network with a tensor network.<n> Experiments demonstrate that QTHA achieves performance comparable to or surpassing LoRA in-efficient fine-tuning.
• Score: 25.45732471566526
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Low-Rank Adaptation (LoRA) enables efficient fine-tuning of pre-trained language models through low-rank matrix approximation, achieving effectiveness in many scenarios. However, its representation capacity is constrained in complex tasks or high-rank dependency settings, potentially limiting model adaptability. To overcome the expressive bottleneck in classical low-rank approximation for fine-tuning large language models (LLMs), we propose Quantum Tensor Hybrid Adaptation (QTHA), a parameter-efficient fine-tuning method that integrates a quantum neural network (QNN) with a tensor network. QTHA explores quantum tensor hybrid fine-tuning within low-rank spaces by decomposing pre-trained weights into quantum neural network and tensor network representations, leveraging quantum state superposition to overcome classical rank limitations. Experiments demonstrate that QTHA achieves performance comparable to or surpassing LoRA in parameter-efficient fine-tuning. Compared to LoRA, QTHA reduces trainable parameters by 76% while reducing training loss by up to 17% and improving test set performance by up to 17% within the same training steps. This research not only enables lightweight adaptation of quantum resources to the billion-parameter models but also validates the feasibility of quantum hardware optimization driven by LLM tasks. It establishes the first engineering-ready foundation for future quantum-enhanced Artificial General Intelligence (AGI) systems.

Related papers

• Hybrid Quantum Recurrent Neural Network For Remaining Useful Life Prediction [67.410870290301]
  We introduce a Hybrid Quantum Recurrent Neural Network framework, combining Quantum Long Short-Term Memory layers with classical dense layers for Remaining Useful Life forecasting. Experimental results demonstrate that, despite having fewer trainable parameters, the Hybrid Quantum Recurrent Neural Network achieves up to a 5% improvement over a Recurrent Neural Network.
  arXiv  Detail & Related papers  (2025-04-29T14:41:41Z)
• Quantum-PEFT: Ultra parameter-efficient fine-tuning [46.145294417722184]
  Quantum-PEFT exploits an underlying full-rank yet surprisingly parameter efficient quantum unitary parameterization.<n>We show that Quantum-PEFT achieves vanishingly smaller number of trainable parameters than the lowest-rank LoRA as dimensions grow.<n>We apply Quantum-PEFT to several transfer learning benchmarks in language and vision, demonstrating significant advantages in parameter efficiency.
  arXiv  Detail & Related papers  (2025-03-07T14:01:25Z)
• RoSTE: An Efficient Quantization-Aware Supervised Fine-Tuning Approach for Large Language Models [95.32315448601241]
  We propose an algorithm named Rotated Straight-Through-Estimator (RoSTE)<n>RoSTE combines quantization-aware supervised fine-tuning (QA-SFT) with an adaptive rotation strategy to reduce activation outliers.<n>Our findings reveal that the prediction error is directly proportional to the quantization error of the converged weights, which can be effectively managed through an optimized rotation configuration.
  arXiv  Detail & Related papers  (2025-02-13T06:44:33Z)
• Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning [5.673361333697935]
  Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning (Dist-QTRL)<n>We introduce Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning (Dist-QTRL)
  arXiv  Detail & Related papers  (2024-12-12T00:51:41Z)
• Leveraging Pre-Trained Neural Networks to Enhance Machine Learning with Variational Quantum Circuits [48.33631905972908]
  We introduce an innovative approach that utilizes pre-trained neural networks to enhance Variational Quantum Circuits (VQC) This technique effectively separates approximation error from qubit count and removes the need for restrictive conditions. Our results extend to applications such as human genome analysis, demonstrating the broad applicability of our approach.
  arXiv  Detail & Related papers  (2024-11-13T12:03:39Z)
• A Quantum Circuit-Based Compression Perspective for Parameter-Efficient Learning [19.178352290785153]
  We introduce Quantum s Adaptation (QPA) in the framework of quantum parameter generation.<n>QPA integrates QNNs with a classical multi-layer perceptron mapping model to generate parameters for fine-tuning methods.<n>Using Gemma-2 and GPT-2 as case studies, QPA demonstrates significant parameter reduction for parameter-efficient fine-tuning methods.
  arXiv  Detail & Related papers  (2024-10-13T14:09:29Z)
• Quantum-Trained Convolutional Neural Network for Deepfake Audio Detection [3.2927352068925444]
  deepfake technologies pose challenges to privacy, security, and information integrity. This paper introduces a Quantum-Trained Convolutional Neural Network framework designed to enhance the detection of deepfake audio.
  arXiv  Detail & Related papers  (2024-10-11T20:52:10Z)
• Quantum-Train with Tensor Network Mapping Model and Distributed Circuit Ansatz [0.8192907805418583]
  Quantum-Train (QT) is a hybrid quantum-classical machine learning framework. It maps quantum state measurements to classical neural network weights. Traditional QT framework employs a multi-layer perceptron (MLP) for this task, but it struggles with scalability and interpretability. We introduce a distributed circuit ansatz designed for large-scale quantum machine learning with multiple small quantum processing unit nodes.
  arXiv  Detail & Related papers  (2024-09-11T03:51:34Z)
• Federated Quantum-Train with Batched Parameter Generation [3.697453416360906]
  We introduce the Federated Quantum-Train (QT) framework, which integrates the QT model into federated learning. Our approach significantly reduces qubit usage from 19 to as low as 8 qubits while reducing generalization error.
  arXiv  Detail & Related papers  (2024-09-04T14:39:11Z)
• Quantum-Train: Rethinking Hybrid Quantum-Classical Machine Learning in the Model Compression Perspective [7.7063925534143705]
  We introduce the Quantum-Train(QT) framework, a novel approach that integrates quantum computing with machine learning algorithms. QT achieves remarkable results by employing a quantum neural network alongside a classical mapping model.
  arXiv  Detail & Related papers  (2024-05-18T14:35:57Z)
• A Quantum-Classical Collaborative Training Architecture Based on Quantum State Fidelity [50.387179833629254]
  We introduce a collaborative classical-quantum architecture called co-TenQu. Co-TenQu enhances a classical deep neural network by up to 41.72% in a fair setting. It outperforms other quantum-based methods by up to 1.9 times and achieves similar accuracy while utilizing 70.59% fewer qubits.
  arXiv  Detail & Related papers  (2024-02-23T14:09:41Z)
• Bridging Classical and Quantum Machine Learning: Knowledge Transfer From Classical to Quantum Neural Networks Using Knowledge Distillation [0.0]
  We present a novel framework for transferring knowledge from classical convolutional neural networks (CNNs) to quantum neural networks (QNNs)<n>We conduct extensive experiments using two parameterized quantum circuits (PQCs) with 4 and 8 qubits on MNIST, Fashion MNIST, and CIFAR10 datasets.<n>Our results establish a promising paradigm for bridging classical deep learning and emerging quantum computing, paving the way for more powerful, resource conscious models in quantum machine intelligence.
  arXiv  Detail & Related papers  (2023-11-23T05:06:43Z)
• OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models [57.27101446992148]
  Large language models (LLMs) have revolutionized natural language processing tasks. Recent post-training quantization (PTQ) methods are effective in reducing memory footprint and improving the computational efficiency of LLM. We introduce an Omnidirectionally calibrated Quantization technique for LLMs, which achieves good performance in diverse quantization settings.
  arXiv  Detail & Related papers  (2023-08-25T02:28:35Z)
• PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models [52.09865918265002]
  We propose a novel quantize before fine-tuning'' framework, PreQuant. PreQuant is compatible with various quantization strategies, with outlier-aware fine-tuning incorporated to correct the induced quantization error. We demonstrate the effectiveness of PreQuant on the GLUE benchmark using BERT, RoBERTa, and T5.
  arXiv  Detail & Related papers  (2023-05-30T08:41:33Z)
• Pre-training Tensor-Train Networks Facilitates Machine Learning with Variational Quantum Circuits [70.97518416003358]
  Variational quantum circuits (VQCs) hold promise for quantum machine learning on noisy intermediate-scale quantum (NISQ) devices. While tensor-train networks (TTNs) can enhance VQC representation and generalization, the resulting hybrid model, TTN-VQC, faces optimization challenges due to the Polyak-Lojasiewicz (PL) condition. To mitigate this challenge, we introduce Pre+TTN-VQC, a pre-trained TTN model combined with a VQC.
  arXiv  Detail & Related papers  (2023-05-18T03:08:18Z)
• Synergy Between Quantum Circuits and Tensor Networks: Short-cutting the Race to Practical Quantum Advantage [43.3054117987806]
  We introduce a scalable procedure for harnessing classical computing resources to provide pre-optimized initializations for quantum circuits. We show this method significantly improves the trainability and performance of PQCs on a variety of problems. By demonstrating a means of boosting limited quantum resources using classical computers, our approach illustrates the promise of this synergy between quantum and quantum-inspired models in quantum computing.
  arXiv  Detail & Related papers  (2022-08-29T15:24:03Z)
• FLIP: A flexible initializer for arbitrarily-sized parametrized quantum circuits [105.54048699217668]
  We propose a FLexible Initializer for arbitrarily-sized Parametrized quantum circuits. FLIP can be applied to any family of PQCs, and instead of relying on a generic set of initial parameters, it is tailored to learn the structure of successful parameters. We illustrate the advantage of using FLIP in three scenarios: a family of problems with proven barren plateaus, PQC training to solve max-cut problem instances, and PQC training for finding the ground state energies of 1D Fermi-Hubbard models.
  arXiv  Detail & Related papers  (2021-03-15T17:38:33Z)
• Quantum circuit architecture search for variational quantum algorithms [88.71725630554758]
  We propose a resource and runtime efficient scheme termed quantum architecture search (QAS) QAS automatically seeks a near-optimal ansatz to balance benefits and side-effects brought by adding more noisy quantum gates. We implement QAS on both the numerical simulator and real quantum hardware, via the IBM cloud, to accomplish data classification and quantum chemistry tasks.
  arXiv  Detail & Related papers  (2020-10-20T12:06:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.