Robust Hybrid Classical-Quantum Transfer Learning Model for Text Classification Using GPT-Neo 125M with LoRA & SMOTE Enhancement
This work addresses text classification for natural language processing applications, presenting an incremental enhancement through hybrid quantum-classical integration.
The researchers tackled text classification by developing a hybrid classical-quantum framework using GPT-Neo 125M with LoRA and SMOTE, which improved accuracy, convergence speed, and generalization compared to the baseline.
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.