用量子计算增强大模型文本分类，提升准确率与收敛速度。
Robust Hybrid Classical-Quantum Transfer Learning Model for Text Classification Using GPT-Neo 125M with LoRA & SMOTE Enhancement
- 结合GPT-Neo 125M、LoRA微调与SMOTE数据增强的混合框架。
- 在IBM 127量子比特和Pennylane 32量子比特上验证有效。
- 适合关注量子增强AI、小样本文本分类的研究者。
本研究提出一种融合经典与量子计算的文本分类混合框架，将GPT-Neo 125M模型与低秩适配（LoRA）及合成少数类过采样技术（SMOTE）结合，并部署于量子计算后端。尽管GPT-Neo 125M基线模型表现最佳，但引入LoRA与SMOTE后，混合模型在准确率、收敛速度和泛化能力上均有提升。实验在IBM 127量子比特硬件与Pennylane 32量子比特仿真环境中完成，验证了经典神经网络与量子电路协同的可行性。该框架展示了混合架构在自然语言处理应用中的潜力。
原文摘要 · Abstract (English)
This research introduces a hybrid classical-quantum framework for text classification, integrating GPT-Neo 125M with Low-Rank Adaptation (LoRA) and Synthetic Minority Over-sampling Technique (SMOTE) using quantum computing backends. While the GPT-Neo 125M baseline remains the best-performing model, the implementation of LoRA and SMOTE enhances the hybrid model, resulting in improved accuracy, faster convergence, and better generalization. Experiments on IBM's 127-qubit quantum backend and Pennylane's 32-qubit simulation demonstrate the viability of combining classical neural networks with quantum circuits. This framework underscores the potential of hybrid architectures for advancing natural language processing applications.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。