# Meta Knowledge Distillation

arXiv: https://arxiv.org/abs/2202.07940 · HTML: https://mlsanity.com/paper/2202.07940/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 35 of its 43 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Placed in

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

## Builds on (most cited first, 30 of 35)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [RandAugment: Practical automated data augmentation with a reduced search space](https://mlsanity.com/paper/1909.13719/) (2019)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [An Empirical Study of Training Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.02057/) (2021)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [When Does Label Smoothing Help?](https://mlsanity.com/paper/1906.02629/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Going deeper with Image Transformers](https://mlsanity.com/paper/2103.17239/) (2021)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers](https://mlsanity.com/paper/2106.10270/) (2021)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [Meta Pseudo Labels](https://mlsanity.com/paper/2003.10580/) (2020)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [Paraphrasing Complex Network: Network Compression via Factor Transfer](https://mlsanity.com/paper/1802.04977/) (2018)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)
- [Adaptive Gradient-Based Meta-Learning Methods](https://mlsanity.com/paper/1906.02717/) (2019)
- [Meta-Gradient Reinforcement Learning](https://mlsanity.com/paper/1805.09801/) (2018)

## Built on by (most cited first, 20 of 20)

- [Curriculum Temperature for Knowledge Distillation](https://mlsanity.com/paper/2211.16231/) (2022)
- [Logit Standardization in Knowledge Distillation](https://mlsanity.com/paper/2403.01427/) (2024)
- [Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information](https://mlsanity.com/paper/2401.08732/) (2024)
- [Categories of Response-Based, Feature-Based, and Relation-Based Knowledge Distillation](https://mlsanity.com/paper/2306.10687/) (2023)
- [Generic-to-Specific Distillation of Masked Autoencoders](https://mlsanity.com/paper/2302.14771/) (2023)
- [Attention Distillation: self-supervised vision transformer students need more guidance](https://mlsanity.com/paper/2210.00944/) (2022)
- [Mitigating Accuracy-Robustness Trade-off via Balanced Multi-Teacher Adversarial Distillation](https://mlsanity.com/paper/2306.16170/) (2023)
- [Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement](https://mlsanity.com/paper/2303.08983/) (2023)
- [GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking](https://mlsanity.com/paper/2305.18144/) (2023)
- [To Cool or not to Cool? Temperature Network Meets Large Foundation Models via DRO](https://mlsanity.com/paper/2404.04575/) (2024)
- [Dynamic Temperature Knowledge Distillation](https://mlsanity.com/paper/2404.12711/) (2024)
- [Distill CLIP (DCLIP): Enhancing Image-Text Retrieval via Cross-Modal Transformer Distillation](https://mlsanity.com/paper/2505.21549/) (2025)
- [Efficient Temporal Sentence Grounding in Videos with Multi-Teacher Knowledge Distillation](https://mlsanity.com/paper/2308.03725/) (2023)
- [Instance Temperature Knowledge Distillation](https://mlsanity.com/paper/2407.00115/) (2024)
- [Adaptive Temperature Based on Logits Correlation in Knowledge Distillation](https://mlsanity.com/paper/2503.09030/) (2025)
- [Swing Distillation: A Privacy-Preserving Knowledge Distillation Framework](https://mlsanity.com/paper/2212.08349/) (2022)
- [Multilingual Sentence-Level Semantic Search using Meta-Distillation Learning](https://mlsanity.com/paper/2309.08185/) (2023)
- [Dynamic Temperature Scheduler for Knowledge Distillation](https://mlsanity.com/paper/2511.13767/) (2025)
- [Consistently Informative Soft-Label Temperature for Knowledge Distillation](https://mlsanity.com/paper/2605.20357/) (2026)
- [Hint-dynamic Knowledge Distillation](https://mlsanity.com/paper/2211.17059/) (2022)

## Abstract (arXiv)

Recent studies pointed out that knowledge distillation (KD) suffers from two degradation problems, the teacher-student gap and the incompatibility with strong data augmentations, making it not applicable to training state-of-the-art models, which are trained with advanced augmentations. However, we observe that a key factor, i.e., the temperatures in the softmax functions for generating probabilities of both the teacher and student models, was mostly overlooked in previous methods. With properly tuned temperatures, such degradation problems of KD can be much mitigated. However, instead of relying on a naive grid search, which shows poor transferability, we propose Meta Knowledge Distillation (MKD) to meta-learn the distillation with learnable meta temperature parameters. The meta parameters are adaptively adjusted during training according to the gradients of the learning objective. We validate that MKD is robust to different dataset scales, different teacher/student architectures, and different types of data augmentation. With MKD, we achieve the best performance with popular ViT architectures among compared methods that use only ImageNet-1K as training data, ranging from tiny to large models. With ViT-L, we achieve 86.5% with 600 epochs of training, 0.6% better than MAE that trains for 1,650 epochs.