SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features

• URL: http://arxiv.org/abs/2608.10709v1
• Date: Tue, 11 Aug 2026 09:29:30 GMT
• Title: SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features
• Abstract summary: 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.
• Score: 7.743324361747458
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy degradation. However, in practical scenarios, training labels are often unavailable due to privacy, copyright, or cost constraints. Knowledge Distillation (KD) is a common approach to address this challenge, but we observe that prior work combining QAT with KD suffers from a fundamental limitation: during distillation, the range mismatch between the teacher and the quantized student model induces an unattainable residual, resulting in an irreducible lower bound on the distillation loss. Motivated by this observation, we propose SQuaT (Student-Aware Quantized Teacher Features), a label-free QAT framework with KD that theoretically eliminates this lower bound by applying the student's quantization parameters to quantize the teacher's features during distillation. Through comprehensive experiments across diverse settings, we demonstrate that SQuaT consistently outperforms strong baselines, with particularly pronounced gains in extreme low-bit (e.g., 1- and 2-bit) settings. Furthermore, extensive evaluations across various model design choices show that our approach does not rely on specific architectural assumptions, making it broadly applicable across diverse architectures and quantization settings. The source code is available at https://github.com/lcdbsa522/SQuaT.

Related papers

• Distillation Traps and Guards: A Calibration Knob for LLM Distillability [54.90137955363471]
  We propose a post-hoc calibration method that enables control over a teacher's distillability via reinforcement fine-tuning.<n>Our objective combines task utility, KL anchor, and across-tokenizer calibration reward.<n> Experiments show that students distilled from distillable teachers outperform SFT and KD baselines.
  arXiv  Detail & Related papers  (2026-04-21T01:22:35Z)
• CR-QAT: Curriculum Relational Quantization-Aware Training for Open-Vocabulary Object Detection [2.751147407342378]
  We propose curriculum relational quantization-aware training (CR-QAT)<n>CR-QAT mitigates error accumulation by partitioning the model for progressive quantization, ensuring stable optimization via error isolation.<n>Experiments on LVIS and zero-shot benchmarks demonstrate that CR-QAT consistently outperforms existing QAT baselines under aggressive low-bit settings.
  arXiv  Detail & Related papers  (2026-03-06T06:57:55Z)
• 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)
• Intra-class Patch Swap for Self-Distillation [3.282914142012984]
  We propose a teacher-free distillation framework based on a single student network.<n>Our approach is built on a simple yet highly effective augmentation, called intra-class patch swap augmentation.<n>Our method consistently outperforms both existing self-distillation baselines and conventional teacher-based KD approaches.
  arXiv  Detail & Related papers  (2025-05-20T09:30:19Z)
• Learning from Stochastic Teacher Representations Using Student-Guided Knowledge Distillation [64.15918654558816]
  Self-distillation (SSD) training strategy is introduced for filtering and weighting teacher representation to distill from task-relevant representations only.<n> Experimental results on real-world affective computing, wearable/biosignal datasets from the UCR Archive, the HAR dataset, and image classification datasets show that the proposed SSD method can outperform state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-04-19T14:08:56Z)
• 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)
• Sinkhorn Distance Minimization for Knowledge Distillation [97.64216712016571]
  Knowledge distillation (KD) has been widely adopted to compress large language models (LLMs) In this paper, we show that the aforementioned KL, RKL, and JS divergences respectively suffer from issues of mode-averaging, mode-collapsing, and mode-underestimation. We propose the Sinkhorn Knowledge Distillation (SinKD) that exploits the Sinkhorn distance to ensure a nuanced and precise assessment of the disparity between teacher and student distributions.
  arXiv  Detail & Related papers  (2024-02-27T01:13:58Z)
• One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation [69.65734716679925]
  Knowledge distillation has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. Most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family. We propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures.
  arXiv  Detail & Related papers  (2023-10-30T11:13:02Z)
• Poster: Self-Supervised Quantization-Aware Knowledge Distillation [6.463799944811755]
  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)
  arXiv  Detail & Related papers  (2023-09-22T23:52:58Z)
• How and When Adversarial Robustness Transfers in Knowledge Distillation? [137.11016173468457]
  This paper studies how and when the adversarial robustness can be transferred from a teacher model to a student model in Knowledge distillation (KD) We show that standard KD training fails to preserve adversarial robustness, and we propose KD with input gradient alignment (KDIGA) for remedy. Under certain assumptions, we prove that the student model using our proposed KDIGA can achieve at least the same certified robustness as the teacher model.
  arXiv  Detail & Related papers  (2021-10-22T21:30:53Z)

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.