# DeepKD: A Deeply Decoupled and Denoised Knowledge Distillation Trainer

arXiv: https://arxiv.org/abs/2505.15133 · HTML: https://mlsanity.com/paper/2505.15133/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 42 of its 60 references that are in the map.
- First posted on arXiv 21 May 2025.

## Placed in

- Knowledge distillation / [General knowledge distillation methods](https://mlsanity.com/distill/general-knowledge-distillation-methods/)

## Builds on (most cited first, 30 of 42)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima](https://mlsanity.com/paper/1609.04836/) (2016)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Visualizing the Loss Landscape of Neural Nets](https://mlsanity.com/paper/1712.09913/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [A Comprehensive Overhaul of Feature Distillation](https://mlsanity.com/paper/1904.01866/) (2019)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Knowledge Distillation with the Reused Teacher Classifier](https://mlsanity.com/paper/2203.14001/) (2022)
- [Cross-Image Relational Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2204.06986/) (2022)
- [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022)
- [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024)
- [Tighter Variational Bounds are Not Necessarily Better](https://mlsanity.com/paper/1802.04537/) (2018)
- [From Knowledge Distillation to Self-Knowledge Distillation: A Unified Approach with Normalized Loss and Customized Soft Labels](https://mlsanity.com/paper/2303.13005/) (2023)
- [Class Attention Transfer Based Knowledge Distillation](https://mlsanity.com/paper/2304.12777/) (2023)
- [Knowledge Diffusion for Distillation](https://mlsanity.com/paper/2305.15712/) (2023)
- [MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models](https://mlsanity.com/paper/2402.01620/) (2024)
- [PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient](https://mlsanity.com/paper/2207.02039/) (2022)
- [Understanding Why Neural Networks Generalize Well Through GSNR of Parameters](https://mlsanity.com/paper/2001.07384/) (2020)

## Built on by (most cited first, 4 of 4)

- [On the Difficulty of Learning a Meta-network for Training Data Selection](https://mlsanity.com/paper/2606.00571/) (2026)
- [Learning Beyond Full Imitation: Task-Preserving Knowledge Distillation](https://mlsanity.com/paper/2609.39338/) (2026)
- [The Gradient That Top-k Distillation Never Computes](https://mlsanity.com/paper/2610.15589/) (2026)
- [CAFE: Confining Feature Distillation to Language-Routed Adapters for Compact Multilingual Automatic Speech Recognition](https://mlsanity.com/paper/2610.19134/) (2026)

## Abstract (arXiv)

Recent advances in knowledge distillation have emphasized the importance of decoupling different knowledge components. While existing methods utilize momentum mechanisms to separate task-oriented and distillation gradients, they overlook the inherent conflict between target-class and non-target-class knowledge flows. Furthermore, low-confidence dark knowledge in non-target classes introduces noisy signals that hinder effective knowledge transfer. To address these limitations, we propose DeepKD, a novel training framework that integrates dual-level decoupling with adaptive denoising. First, through theoretical analysis of gradient signal-to-noise ratio (GSNR) characteristics in task-oriented and non-task-oriented knowledge distillation, we design independent momentum updaters for each component to prevent mutual interference. We observe that the optimal momentum coefficients for task-oriented gradient (TOG), target-class gradient (TCG), and non-target-class gradient (NCG) should be positively related to their GSNR. Second, we introduce a dynamic top-k mask (DTM) mechanism that gradually increases K from a small initial value to incorporate more non-target classes as training progresses, following curriculum learning principles. The DTM jointly filters low-confidence logits from both teacher and student models, effectively purifying dark knowledge during early training. Extensive experiments on CIFAR-100, ImageNet, and MS-COCO demonstrate DeepKD's effectiveness. Our code is available at https://github.com/haiduo/DeepKD.