Hybrid Quantum-Classical NLP Classification with Compact Semantic Representations: An Experimental Analysis of Representation Compression

• URL: http://arxiv.org/abs/2609.10089v1
• Date: Wed, 09 Sep 2026 12:09:50 GMT
• Title: Hybrid Quantum-Classical NLP Classification with Compact Semantic Representations: An Experimental Analysis of Representation Compression
• Abstract summary: Large language and sentence-embedding models provide rich semantic representations, but their high dimensionality poses a challenge for machine learning.<n>We investigate a hybrid quantum-classical pipeline that transforms high-dimensional sentence embeddings into compact representations for variational quantum classification.<n>We show that supervised dimensionality reduction can preserve task-relevant information far more effectively than variance-based compression.
• Score: 4.18874340076966
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language and sentence-embedding models provide rich semantic representations, but their high dimensionality poses a challenge for near-term quantum machine learning (QML), where quantum circuits can process only a limited number of input features. We investigate a hybrid quantum-classical pipeline that transforms high-dimensional sentence embeddings into compact representations for variational quantum classification. The workflow combines a pretrained sentence-embedding model, dimensionality reduction, angle encoding, a variational quantum circuit (VQC), and a classical decision layer. We systematically compare principal component analysis (PCA), neighborhood components analysis (NCA), and linear discriminant analysis (LDA), covering both unsupervised and supervised dimensionality reduction. Using the TREC question-classification dataset, we study the relationship between representation dimensionality, information retention, qubit count, and classification performance. Preliminary PCA experiments reveal a strong information bottleneck: reducing 768-dimensional embeddings to 3, 4, 5, and 8 dimensions retains about 8.2%, 10.2%, 11.9%, and 16.4% of the variance, with corresponding classification accuracies of 50.3%, 51.2%, 57.9%, and 63.4%. In contrast, supervised reduction is substantially more efficient. LDA reaches 85.3% accuracy and NCA reaches 83.1% using only 5 dimensions, under a leakage-free cross-validation protocol, compared with 85.1% for a full 384-dimensional classical baseline. These results indicate that supervised dimensionality reduction can preserve task-relevant information far more effectively than variance-based compression, making compact representations a promising route toward practical hybrid quantum-classical NLP models.

Related papers

• QTrans: A Quantum Transformer for Sentiment Classification [30.090297417712502]
  We propose a model named QTrans, which uses parameterized quantum circuits to construct query, key, and value features.<n> Experimental results on the MR, CR, and MPQA datasets show that QTrans achieves test accuracies of 72.13%, 69.51%, and 63.45%, respectively.
  arXiv  Detail & Related papers  (2026-09-10T06:04:31Z)
• Quantum-Inspired Hybrid Neural Networks for Neural Decoding: A Controlled Ablation Study of Learnable Quantum Sidecar Integration [5.2726003549534655]
  We study parameterized quantum circuits (PQCs) integrated as residual sidecar modules within a ResNet-50 backbone for neural population decoding.<n>We compare four model variants: baseline, quantum sidecar with frozen input projection, quantum sidecar with backbone-gradient-trained projection, and a measurement-guided variant that aligns angle encodings with circuit measurement outcomes.
  arXiv  Detail & Related papers  (2026-08-23T15:55:43Z)
• Evaluation of Variational Quantum Classifiers (VQC) for Cyberattack Detection in the NISQ Era [0.0]
  Variational Quantums (VQC) can detect network anomalies in the era of Noisy Intermediate-Scale Quantum (NISQ) systems.<n>Model was trained on a class-balanced set spanning the 22 raw NSL-KDD attack categories and evaluated as a probe of representational capacity.<n>We interpret this behavior as consistent with the loss of linear separability induced by excessive compression.
  arXiv  Detail & Related papers  (2026-06-19T20:00:48Z)
• BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models [56.504879072674015]
  We propose Bit-Plane Decomposition Quantization (BPDQ), which constructs a variable quantization grid via bit-planes and scalar coefficients.<n>BPDQ enables serving Qwen2.5-72B on a single GTX 3090 with 83.85% GSM8K accuracy (vs. 90.83% at 16-bit)
  arXiv  Detail & Related papers  (2026-02-04T02:54:37Z)
• JTok: On Token Embedding as another Axis of Scaling Law via Joint Token Self-modulation [46.64215658042213]
  We introduce Joint-Token (JTok) and Mixture of Joint-Token (JTok-M), which augment Transformer layers with modulation vectors retrieved from auxiliary embedding tables.<n>These vectors modulate the backbone via lightweight, element-wise operations, incurring negligible FLOPs overhead.<n>Our approach consistently reduces validation loss and significantly improves downstream task performance.
  arXiv  Detail & Related papers  (2026-01-31T16:15:18Z)
• Exploring Layer-wise Information Effectiveness for Post-Training Quantization in Small Language Models [4.238165821317982]
  LieQ is a metric-driven framework that addresses the challenge of maintaining accuracy in sub-7B models under extreme low-bit compression.<n>Our method introduces three complementary layer-wise diagnostics-Perplexity Drop, Representational Compactness, and Top-k Energy Gain.<n>On Qwen3-4B, LieQ recovers 95.9% of FP16 baseline performance at 2.05-bit quantization, outperforming GPTQ by 19.7% and AWQ by 18.1% on average across seven zero-shot reasoning tasks.
  arXiv  Detail & Related papers  (2025-08-05T11:17:04Z)
• Optimization of embeddings storage for RAG systems using quantization and dimensionality reduction techniques [0.0]
  We show that float8 quantization achieves a 4x storage reduction with minimal performance degradation.<n> PCA emerges as the most effective dimensionality reduction technique.<n>We propose a methodology based on visualizing the performance-storage trade-off space to identify the optimal configuration.
  arXiv  Detail & Related papers  (2025-04-30T18:20:16Z)
• Quantum Transfer Learning for MNIST Classification Using a Hybrid Quantum-Classical Approach [0.0]
  We implement a hybrid quantum-classical model for image classification that compresses MNIST digit images into a low-dimensional feature space.<n>An autoencoder compresses each $28times28$ image (784 pixels) into a 64-dimensional latent vector.<n>We map these features onto a 5-qubit quantum state.
  arXiv  Detail & Related papers  (2024-08-05T22:16:27Z)
• Data-free Weight Compress and Denoise for Large Language Models [96.68582094536032]
  We propose a novel approach termed Data-free Joint Rank-k Approximation for compressing the parameter matrices.<n>We achieve a model pruning of 80% parameters while retaining 93.43% of the original performance without any calibration data.
  arXiv  Detail & Related papers  (2024-02-26T05:51:47Z)
• KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization [67.74400574357472]
  LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference.<n> Quantization is a promising approach for compressing KV cache activations; however, existing solutions fail to represent activations accurately in sub-4-bit precision.<n>Our work, KVQuant, facilitates low precision KV cache quantization by incorporating several novel methods.
  arXiv  Detail & Related papers  (2024-01-31T18:58:14Z)
• Quantum machine learning for image classification [39.58317527488534]
  This research introduces two quantum machine learning models that leverage the principles of quantum mechanics for effective computations. Our first model, a hybrid quantum neural network with parallel quantum circuits, enables the execution of computations even in the noisy intermediate-scale quantum era. A second model introduces a hybrid quantum neural network with a Quanvolutional layer, reducing image resolution via a convolution process.
  arXiv  Detail & Related papers  (2023-04-18T18:23:20Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.