Robust Hybrid Classical-Quantum Transfer Learning Model for Text Classification Using GPT-Neo 125M with LoRA & SMOTE Enhancement

Santanam Wishal
1/12/2025
cs.LGquant-ph

No official code found. Best implementation: kianaaa19/leopold (0 stars, last commit 2025-01-07).

Abstract

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.

View on arXivView PDF

Code Implementations(1)

kianaaa19/leopoldCommunity100%

LEOPOLD: A Robust Hybrid Classical-Quantum Transfer Learning Model for Text Classification Using GPT-Neo 125M with LoRA & SMOTE Enhancement

00Jupyter NotebookJan 4, 20251 years ago

Similar Papers

A Hybrid Classical-Quantum Fine Tuned BERT for Text Classification

89% match2025

Quantum-Enhanced Natural Language Generation: A Multi-Model Framework with Hybrid Quantum-Classical Architectures

86% match2025

Quantum Convolutional Neural Network: A Hybrid Quantum-Classical Approach for Iris Dataset Classification

86% match2024

Disentangling Quantum and Classical Contributions in Hybrid Quantum Machine Learning Architectures

86% match2023

Quantum Transfer Learning for Acceptability Judgements

86% match2024

Hybrid Quantum-Classical Selective State Space Artificial Intelligence

85% match2025

Cite this paper

@article{wishal2025robust,
  title  = {Robust Hybrid Classical-Quantum Transfer Learning Model for Text Classification Using GPT-Neo 125M with LoRA & SMOTE Enhancement},
  author = {Santanam Wishal},
  year   = {2025},
  eprint = {2501.10435},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2501.10435v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2501.10435.svg)](https://codeofpaper.com/paper/2501.10435)

Discussion