# Hint-dynamic Knowledge Distillation

arXiv: https://arxiv.org/abs/2211.17059 · HTML: https://mlsanity.com/paper/2211.17059/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 24 of its 27 references that are in the map.
- First posted on arXiv 30 Nov 2022.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [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)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [HRank: Filter Pruning using High-Rank Feature Map](https://mlsanity.com/paper/2002.10179/) (2020)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [Quantized Convolutional Neural Networks for Mobile Devices](https://mlsanity.com/paper/1512.06473/) (2015)
- [Compressing Deep Convolutional Networks using Vector Quantization](https://mlsanity.com/paper/1412.6115/) (2014)
- [Knowledge Distillation from Internal Representations](https://mlsanity.com/paper/1910.03723/) (2019)
- [Learnable Companding Quantization for Accurate Low-bit Neural Networks](https://mlsanity.com/paper/2103.07156/) (2021)
- [Complementary Relation Contrastive Distillation](https://mlsanity.com/paper/2103.16367/) (2021)
- [Dynamic Knowledge Distillation for Pre-trained Language Models](https://mlsanity.com/paper/2109.11295/) (2021)
- [Domain Generalization on Medical Imaging Classification using Episodic Training with Task Augmentation](https://mlsanity.com/paper/2106.06908/) (2021)
- [Spot-adaptive Knowledge Distillation](https://mlsanity.com/paper/2205.02399/) (2022)
- [Meta Knowledge Distillation](https://mlsanity.com/paper/2202.07940/) (2022)
- [Knowledge Condensation Distillation](https://mlsanity.com/paper/2207.05409/) (2022)
- [Hierarchical Deep Network with Uncertainty-aware Semi-supervised Learning for Vessel Segmentation](https://mlsanity.com/paper/2105.14732/) (2021)

## Abstract (arXiv)

Knowledge Distillation (KD) transfers the knowledge from a high-capacity teacher model to promote a smaller student model. Existing efforts guide the distillation by matching their prediction logits, feature embedding, etc., while leaving how to efficiently utilize them in junction less explored. In this paper, we propose Hint-dynamic Knowledge Distillation, dubbed HKD, which excavates the knowledge from the teacher' s hints in a dynamic scheme. The guidance effect from the knowledge hints usually varies in different instances and learning stages, which motivates us to customize a specific hint-learning manner for each instance adaptively. Specifically, a meta-weight network is introduced to generate the instance-wise weight coefficients about knowledge hints in the perception of the dynamical learning progress of the student model. We further present a weight ensembling strategy to eliminate the potential bias of coefficient estimation by exploiting the historical statics. Experiments on standard benchmarks of CIFAR-100 and Tiny-ImageNet manifest that the proposed HKD well boost the effect of knowledge distillation tasks.