用8个量子比特实现高效文本分类，精度超经典模型。
CLAQS: Compact Learnable All-Quantum Token Mixer with Shared-ansatz for Text Classification
- 设计紧凑量子混洗器，统一学习复数混合与非线性变换。
- 在SST-2和IMDB上分别达91.64%和87.08%准确率。
- 适合资源受限的量子计算场景，易训练且可扩展至长序列。
量子计算正快速扩展，从云端量子处理器到高性能GPU模拟器，为超越玩具任务的量子自然语言处理提供了契机。然而设备仍受限于量子比特数量和电路深度，训练不稳定，且经典注意力机制计算与内存开销大。为此，我们提出CLAQS——一种紧凑、相位感知的全量子文本混洗器，能在统一量子电路中联合学习复数混合与非线性变换。为实现稳定端到端优化，采用l1归一化调控幅度增长，并引入两阶段参数化量子架构，将共享的词嵌入与窗口级量子前馈模块解耦。在滑动窗口机制下结合文档级聚合，仅需8个数据量子比特与浅层电路，即在SST-2上达到91.64%准确率，在IMDB上达87.08%，优于经典Transformer基线及强健的混合量子-经典模型。
原文摘要 · Abstract (English)
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.
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。