Robust Hybrid Classical-Quantum Transfer Learning Model for Text Classification Using GPT-Neo 125M with LoRA & SMOTE Enhancement
Fuente:
arXiv
Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917899255414784 |
|---|---|
| author | Wishal, Santanam |
| author_facet | Wishal, Santanam |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_10435 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Robust Hybrid Classical-Quantum Transfer Learning Model for Text Classification Using GPT-Neo 125M with LoRA & SMOTE Enhancement Wishal, Santanam Machine Learning Quantum Physics 68T50 (Primary), 65Y05 (Secondary) I.2.7 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. |
| title | Robust Hybrid Classical-Quantum Transfer Learning Model for Text Classification Using GPT-Neo 125M with LoRA & SMOTE Enhancement |
| topic | Machine Learning Quantum Physics 68T50 (Primary), 65Y05 (Secondary) I.2.7 |
| url | https://arxiv.org/abs/2501.10435 |