Synthetic Adaptive Guided Embeddings (SAGE): A Novel Knowledge Distillation Method

• URL: http://arxiv.org/abs/2508.14783v1
• Date: Wed, 20 Aug 2025 15:29:00 GMT
• Title: Synthetic Adaptive Guided Embeddings (SAGE): A Novel Knowledge Distillation Method
• Authors: Suleyman Olcay Polat, Poli A. Nemkova, Mark V. Albert,
• Abstract summary: We propose a novel adaptive distillation framework that dynamically augments training data in regions of high student model loss.<n>Our method identifies underperforming regions in the embedding space and generates targeted synthetic examples to guide student learning.
• Score: 1.5839621757142595
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Model distillation enables the transfer of knowledge from large-scale models to compact student models, facilitating deployment in resource-constrained environments. However, conventional distillation approaches often suffer from computational overhead and limited generalization. We propose a novel adaptive distillation framework that dynamically augments training data in regions of high student model loss. Using UMAP-based dimensionality reduction and nearest neighbor sampling, our method identifies underperforming regions in the embedding space and generates targeted synthetic examples to guide student learning. To further improve efficiency, we introduce a lightweight teacher-student interface that bypasses the teacher's input layer, enabling direct distillation on vectorized representations. Experiments across standard NLP benchmarks demonstrate that our 66M-parameter student model consistently matches or surpasses established baselines, achieving 91.2% on QNLI and 92.3% on SST-2, while training with fewer epochs. These results highlight the promise of loss-aware data augmentation and vectorized distillation for efficient and effective model compression.

Related papers

• ReDiF: Reinforced Distillation for Few Step Diffusion [21.686373820429736]
  Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps.<n>We propose a reinforcement learning based distillation framework for diffusion models.
  arXiv  Detail & Related papers  (2025-12-28T06:27:24Z)
• 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)
• Ultra-Resolution Adaptation with Ease [62.56434979517156]
  We propose a set of key guidelines for ultra-resolution adaptation termed emphURAE.<n>We show that tuning minor components of the weight matrices outperforms widely-used low-rank adapters when synthetic data are unavailable.<n>Experiments validate that URAE achieves comparable 2K-generation performance to state-of-the-art closed-source models like FLUX1.1 [Pro] Ultra with only 3K samples and 2K iterations.
  arXiv  Detail & Related papers  (2025-03-20T16:44:43Z)
• Denoising Score Distillation: From Noisy Diffusion Pretraining to One-Step High-Quality Generation [82.39763984380625]
  We introduce denoising score distillation (DSD), a surprisingly effective and novel approach for training high-quality generative models from low-quality data.<n>DSD pretrains a diffusion model exclusively on noisy, corrupted samples and then distills it into a one-step generator capable of producing refined, clean outputs.
  arXiv  Detail & Related papers  (2025-03-10T17:44:46Z)
• Efficient Point Cloud Classification via Offline Distillation Framework and Negative-Weight Self-Distillation Technique [46.266960248570086]
  We introduce an innovative offline recording strategy that avoids the simultaneous loading of both teacher and student models. This approach feeds a multitude of augmented samples into the teacher model, recording both the data augmentation parameters and the corresponding logit outputs. Experimental results demonstrate that the proposed distillation strategy enables the student model to achieve performance comparable to state-of-the-art models.
  arXiv  Detail & Related papers  (2024-09-03T16:12:12Z)
• Adv-KD: Adversarial Knowledge Distillation for Faster Diffusion Sampling [2.91204440475204]
  Diffusion Probabilistic Models (DPMs) have emerged as a powerful class of deep generative models. They rely on sequential denoising steps during sample generation. We propose a novel method that integrates denoising phases directly into the model's architecture.
  arXiv  Detail & Related papers  (2024-05-31T08:19:44Z)
• Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion [29.297959023968165]
  This paper proposes a progressive distillation method based on masked generation features for KGC task. Specifically, we perform pre-distillation on PLM to obtain high-quality teacher models, and compress the PLM network to obtain multi-grade student models. The experimental results demonstrate that the model in the pre-distillation stage surpasses the existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-19T07:34:36Z)
• BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping [64.54271680071373]
  Diffusion models have demonstrated excellent potential for generating diverse images. Knowledge distillation has been recently proposed as a remedy that can reduce the number of inference steps to one or a few. We present a novel technique called BOOT, that overcomes limitations with an efficient data-free distillation algorithm.
  arXiv  Detail & Related papers  (2023-06-08T20:30:55Z)
• EmbedDistill: A Geometric Knowledge Distillation for Information Retrieval [83.79667141681418]
  Large neural models (such as Transformers) achieve state-of-the-art performance for information retrieval (IR) We propose a novel distillation approach that leverages the relative geometry among queries and documents learned by the large teacher model. We show that our approach successfully distills from both dual-encoder (DE) and cross-encoder (CE) teacher models to 1/10th size asymmetric students that can retain 95-97% of the teacher performance.
  arXiv  Detail & Related papers  (2023-01-27T22:04:37Z)
• Self-Feature Regularization: Self-Feature Distillation Without Teacher Models [0.0]
  Self-Feature Regularization(SFR) is proposed, which uses features in the deep layers to supervise feature learning in the shallow layers. We firstly use generalization-l2 loss to match local features and a many-to-one approach to distill more intensively in the channel dimension.
  arXiv  Detail & Related papers  (2021-03-12T15:29:00Z)

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.