Poster: Self-Supervised Quantization-Aware Knowledge Distillation

• URL: http://arxiv.org/abs/2309.13220v1
• Date: Fri, 22 Sep 2023 23:52:58 GMT
• Title: Poster: Self-Supervised Quantization-Aware Knowledge Distillation
• Abstract summary: Quantization-aware training (QAT) starts with a pre-trained full-precision model and performs quantization during retraining. Existing QAT works require supervision from the labels and they suffer from accuracy loss due to reduced precision. This paper proposes a novel Self-Supervised Quantization-Aware Knowledge Distillation framework (SQAKD)
• Score: 6.463799944811755
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantization-aware training (QAT) starts with a pre-trained full-precision model and performs quantization during retraining. However, existing QAT works require supervision from the labels and they suffer from accuracy loss due to reduced precision. To address these limitations, this paper proposes a novel Self-Supervised Quantization-Aware Knowledge Distillation framework (SQAKD). SQAKD first unifies the forward and backward dynamics of various quantization functions and then reframes QAT as a co-optimization problem that simultaneously minimizes the KL-Loss and the discretization error, in a self-supervised manner. The evaluation shows that SQAKD significantly improves the performance of various state-of-the-art QAT works. SQAKD establishes stronger baselines and does not require extensive labeled training data, potentially making state-of-the-art QAT research more accessible.

Related papers

• A Target-Centric Survey of Quantization-Aware Training [53.52583463060327]
  Quantization-Aware Training (QAT) techniques have emerged as a promising solution to address these challenges.<n>QAT techniques explicitly simulate quantization effects during model training, yielding low-bit models that achieve accuracy comparable to their full-precision counterparts.
  arXiv  Detail & Related papers  (2026-08-30T09:04:47Z)
• SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features [7.743324361747458]
  Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy degradation.<n>Knowledge Distillation (KD) is a common approach to address this challenge.<n>We propose SQuaT, a label-free QAT framework with KD that theoretically eliminates this lower bound.
  arXiv  Detail & Related papers  (2026-08-11T09:29:30Z)
• LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization [9.37026660976194]
  Quantization-aware training (QAT) is essential for extremely low-bit large language models (LLMs)<n>We propose LC-QAT, a 2-bit weight-only VQ-QAT framework that represents quantized weights via a learned affine mapping over discrete vectors.<n>We show that LC-QAT consistently outperforms state-of-the-art QAT methods while using only 0.1%--10% of the training data.
  arXiv  Detail & Related papers  (2026-06-09T08:02:56Z)
• StableQAT: Stable Quantization-Aware Training at Ultra-Low Bitwidths [49.94623294999562]
  Quantization-aware training (QAT) is essential for deploying large models under strict memory and latency constraints.<n>Common approaches based on the straight-through estimator (STE) or soft quantizers often suffer from mismatch, instability, or high computational overhead.<n>We propose StableQAT, a unified and efficient QAT framework that stabilizes training in ultra low-bit settings.
  arXiv  Detail & Related papers  (2026-01-27T08:00:57Z)
• What Makes Low-Bit Quantization-Aware Training Work for Reasoning LLMs? A Systematic Study [59.44848132298657]
  Post-training quantization (PTQ) usually comes with the cost of large accuracy drops, especially for reasoning tasks under low-bit settings.<n>In this study, we present a systematic empirical study of quantization-aware training (QAT) for reasoning models.
  arXiv  Detail & Related papers  (2026-01-21T11:22:29Z)
• CAGE: Curvature-Aware Gradient Estimation For Accurate Quantization-Aware Training [73.46600457802693]
  We introduce a new method that counteracts the loss induced by quantization.<n>CAGE significantly improves upon the state-of-theart methods in terms of accuracy, for similar computational cost.<n>For QAT pre-training of Llama models, CAGE matches the accuracy achieved at 4-bits (W4A4) with the prior best method.
  arXiv  Detail & Related papers  (2025-10-21T16:33:57Z)
• Sparse Query Attention (SQA): A Computationally Efficient Attention Mechanism with Query Heads Reduction [0.0]
  This paper introduces Sparse Query Attention (SQA), a novel attention architecture that pursues an alternative and complementary optimization path.<n>It can achieve significant throughput improvements of up to 3x in computation-bound scenarios such as model pre-training, fine-tuning, and encoder-based tasks.<n>SQA was discovered serendipitously during the development of the upcoming Reactive Transformer architecture.
  arXiv  Detail & Related papers  (2025-10-02T09:01:38Z)
• Compute-Optimal Quantization-Aware Training [50.98555000360485]
  Quantization-aware training (QAT) is a leading technique for improving the accuracy of quantized neural networks.<n>Previous work has shown that decomposing training into a full-precision (FP) phase followed by a QAT phase yields superior accuracy.<n>We investigate how different QAT durations impact final performance.
  arXiv  Detail & Related papers  (2025-09-26T21:09:54Z)
• Data-Augmented Quantization-Aware Knowledge Distillation [1.8126132932201138]
  Quantization-aware training (QAT) and Knowledge Distillation (KD) are combined to achieve competitive performance in creating low-bit deep learning models.<n>The relationship between quantization-aware KD and data augmentation (DA) remains unexplored.<n>We propose a novel metric which evaluates DAs according to their capacity to maximize the Contextual Mutual Information.
  arXiv  Detail & Related papers  (2025-09-04T03:24:35Z)
• FIMA-Q: Post-Training Quantization for Vision Transformers by Fisher Information Matrix Approximation [55.12070409045766]
  Post-training quantization (PTQ) has stood out as a cost-effective and promising model compression paradigm in recent years.<n>Current PTQ methods for Vision Transformers (ViTs) still suffer from significant accuracy degradation, especially under low-bit quantization.
  arXiv  Detail & Related papers  (2025-06-13T07:57:38Z)
• Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization [0.0]
  Layer-wise PTQ is a promising technique for compressing large language models (LLMs)<n>Recent progress in this area is saturating, underscoring the need to revisit its core limitations and explore further improvements.<n>We propose Quantization Error Propagation (QEP), a general, lightweight, and scalable framework that enhances layer-wise PTQ by explicitly propagating quantization errors and compensating for accumulated errors.
  arXiv  Detail & Related papers  (2025-04-13T15:56:00Z)
• Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix [0.7261171488281837]
  We find that the sharp landscape of loss, which leads to a dramatic performance drop, is an essential factor that causes instability. We propose Feature-Perturbed Quantization (FPQ) to generalize and employ the feature distillation method to the quantized model.
  arXiv  Detail & Related papers  (2025-03-14T07:56:20Z)
• Dual Ensembled Multiagent Q-Learning with Hypernet Regularizer [62.01554688056335]
  Overestimation in the multiagent setting has received comparatively little attention. We propose a novel hypernet regularizer on hypernetwork weights and biases to constrain the optimization of online global Q-network to prevent overestimation accumulation.
  arXiv  Detail & Related papers  (2025-02-04T05:14:58Z)
• High-Fidelity Coherent-One-Way QKD Simulation Framework for 6G Networks: Bridging Theory and Reality [105.73011353120471]
  Quantum key distribution (QKD) has been emerged as a promising solution for guaranteeing information-theoretic security. Due to the considerable high-cost of QKD equipment, a lack of QKD communication system design tools is challenging. This paper introduces a QKD communication system design tool.
  arXiv  Detail & Related papers  (2025-01-21T11:03:59Z)
• QSpec: Speculative Decoding with Complementary Quantization Schemes [37.007621357142725]
  Quantization has been substantially adopted to accelerate inference and reduce memory consumption of large language models. We propose a novel quantization paradigm called QSPEC, which seamlessly integrates two complementary quantization schemes for speculative decoding. QSPEC empirically boosts token generation throughput by up to 1.80x without any quality compromise.
  arXiv  Detail & Related papers  (2024-10-15T05:57:51Z)
• Boosting CLIP Adaptation for Image Quality Assessment via Meta-Prompt Learning and Gradient Regularization [55.09893295671917]
  This paper introduces a novel Gradient-Regulated Meta-Prompt IQA Framework (GRMP-IQA) The GRMP-IQA comprises two key modules: Meta-Prompt Pre-training Module and Quality-Aware Gradient Regularization. Experiments on five standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods under limited data setting.
  arXiv  Detail & Related papers  (2024-09-09T07:26:21Z)
• Self-Supervised Quantization-Aware Knowledge Distillation [5.4714555711042]
  This paper proposes a novel Self-Supervised Quantization-Aware Knowledge Distillation (SQAKD) framework. SQAKD unifies the forward and backward dynamics of various quantization functions, making it flexible for incorporating various QAT works. A comprehensive evaluation shows that SQAKD substantially outperforms the state-of-the-art QAT and KD works for a variety of model architectures.
  arXiv  Detail & Related papers  (2024-03-17T06:20:28Z)
• Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech [50.95292368372455]
  We propose VQScore, a self-supervised metric for evaluating speech based on the quantization error of a vector-quantized-variational autoencoder (VQ-VAE) The training of VQ-VAE relies on clean speech; hence, large quantization errors can be expected when the speech is distorted. We found that the vector quantization mechanism could also be used for self-supervised speech enhancement (SE) model training.
  arXiv  Detail & Related papers  (2024-02-26T06:01:38Z)
• Push Quantization-Aware Training Toward Full Precision Performances via Consistency Regularization [23.085230108628707]
  Quantization-Aware Training (QAT) methods intensively depend on the complete labeled dataset or knowledge distillation to guarantee the performances toward Full Precision (FP) accuracies. We present a simple, novel, yet powerful method introducing an Consistency Regularization (CR) for QAT. Our method generalizes well to different network architectures and various QAT methods.
  arXiv  Detail & Related papers  (2024-02-21T03:19:48Z)
• Challenges for Reinforcement Learning in Quantum Circuit Design [8.894627352356302]
  Hybrid quantum machine learning (QML) comprises both the application of QC to improve machine learning (ML) and ML to improve QC architectures. We propose qcd-gym, a concrete framework formalized as a Markov decision process, to enable learning policies capable of controlling a universal set of continuously parameterized quantum gates.
  arXiv  Detail & Related papers  (2023-12-18T16:41:30Z)
• Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL [86.0987896274354]
  We first identify a fundamental pattern, self-excitation, as the primary cause of Q-value estimation divergence in offline RL. We then propose a novel Self-Excite Eigenvalue Measure (SEEM) metric to measure the evolving property of Q-network at training. For the first time, our theory can reliably decide whether the training will diverge at an early stage.
  arXiv  Detail & Related papers  (2023-10-06T17:57:44Z)
• SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization [13.075574481614478]
  One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete representation uses only a fraction of the full capacity of the codebook. We propose a new training scheme that extends the standard VAE via novel dequantization and quantization. Our experiments show that SQ-VAE improves codebook utilization without using commons.
  arXiv  Detail & Related papers  (2022-05-16T09:49:37Z)
• ProQA: Structural Prompt-based Pre-training for Unified Question Answering [84.59636806421204]
  ProQA is a unified QA paradigm that solves various tasks through a single model. It concurrently models the knowledge generalization for all QA tasks while keeping the knowledge customization for every specific QA task. ProQA consistently boosts performance on both full data fine-tuning, few-shot learning, and zero-shot testing scenarios.
  arXiv  Detail & Related papers  (2022-05-09T04:59:26Z)
• Quantum circuit architecture search on a superconducting processor [56.04169357427682]
  Variational quantum algorithms (VQAs) have shown strong evidences to gain provable computational advantages for diverse fields such as finance, machine learning, and chemistry. However, the ansatz exploited in modern VQAs is incapable of balancing the tradeoff between expressivity and trainability. We demonstrate the first proof-of-principle experiment of applying an efficient automatic ansatz design technique to enhance VQAs on an 8-qubit superconducting quantum processor.
  arXiv  Detail & Related papers  (2022-01-04T01:53:42Z)
• Task-Specific Normalization for Continual Learning of Blind Image Quality Models [105.03239956378465]
  We present a simple yet effective continual learning method for blind image quality assessment (BIQA) The key step in our approach is to freeze all convolution filters of a pre-trained deep neural network (DNN) for an explicit promise of stability. We assign each new IQA dataset (i.e., task) a prediction head, and load the corresponding normalization parameters to produce a quality score. The final quality estimate is computed by black a weighted summation of predictions from all heads with a lightweight $K$-means gating mechanism.
  arXiv  Detail & Related papers  (2021-07-28T15:21:01Z)

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.