CLAQS: Compact Learnable All-Quantum Token Mixer with Shared-ansatz for Text Classification
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909830938099712 |
|---|---|
| author | Chen, Junhao Zhou, Yifan Jiang, Hanqi Pan, Yi Li, Yiwei Zhao, Huaqin Zhang, Wei Wang, Yingfeng Liu, Tianming |
| author_facet | Chen, Junhao Zhou, Yifan Jiang, Hanqi Pan, Yi Li, Yiwei Zhao, Huaqin Zhang, Wei Wang, Yingfeng Liu, Tianming |
| contents | Quantum compute is scaling fast, from cloud QPUs to high throughput GPU simulators, making it timely to prototype quantum NLP beyond toy tasks. However, devices remain qubit limited and depth limited, training can be unstable, and classical attention is compute and memory heavy. This motivates compact, phase aware quantum token mixers that stabilize amplitudes and scale to long sequences. We present CLAQS, a compact, fully quantum token mixer for text classification that jointly learns complex-valued mixing and nonlinear transformations within a unified quantum circuit. To enable stable end-to-end optimization, we apply l1 normalization to regulate amplitude scaling and introduce a two-stage parameterized quantum architecture that decouples shared token embeddings from a window-level quantum feed-forward module. Operating under a sliding-window regime with document-level aggregation, CLAQS requires only eight data qubits and shallow circuits, yet achieves 91.64% accuracy on SST-2 and 87.08% on IMDB, outperforming both classical Transformer baselines and strong hybrid quantum-classical counterparts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06532 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CLAQS: Compact Learnable All-Quantum Token Mixer with Shared-ansatz for Text Classification Chen, Junhao Zhou, Yifan Jiang, Hanqi Pan, Yi Li, Yiwei Zhao, Huaqin Zhang, Wei Wang, Yingfeng Liu, Tianming Quantum Physics Artificial Intelligence Quantum compute is scaling fast, from cloud QPUs to high throughput GPU simulators, making it timely to prototype quantum NLP beyond toy tasks. However, devices remain qubit limited and depth limited, training can be unstable, and classical attention is compute and memory heavy. This motivates compact, phase aware quantum token mixers that stabilize amplitudes and scale to long sequences. We present CLAQS, a compact, fully quantum token mixer for text classification that jointly learns complex-valued mixing and nonlinear transformations within a unified quantum circuit. To enable stable end-to-end optimization, we apply l1 normalization to regulate amplitude scaling and introduce a two-stage parameterized quantum architecture that decouples shared token embeddings from a window-level quantum feed-forward module. Operating under a sliding-window regime with document-level aggregation, CLAQS requires only eight data qubits and shallow circuits, yet achieves 91.64% accuracy on SST-2 and 87.08% on IMDB, outperforming both classical Transformer baselines and strong hybrid quantum-classical counterparts. |
| title | CLAQS: Compact Learnable All-Quantum Token Mixer with Shared-ansatz for Text Classification |
| topic | Quantum Physics Artificial Intelligence |
| url | https://arxiv.org/abs/2510.06532 |