# Estimating and Maximizing Mutual Information for Knowledge Distillation

arXiv: https://arxiv.org/abs/2110.15946 · HTML: https://mlsanity.com/paper/2110.15946/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 29 of its 63 references that are in the map.
- First posted on arXiv 29 Oct 2021.

## Placed in

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

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Visualizing and Understanding Convolutional Networks](https://mlsanity.com/paper/1311.2901/) (2013)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [Variational Information Distillation for Knowledge Transfer](https://mlsanity.com/paper/1904.05835/) (2019)
- [Correlation Congruence for Knowledge Distillation](https://mlsanity.com/paper/1904.01802/) (2019)
- [Data-Driven Sparse Structure Selection for Deep Neural Networks](https://mlsanity.com/paper/1707.01213/) (2017)
- [Black-box Explanation of Object Detectors via Saliency Maps](https://mlsanity.com/paper/2006.03204/) (2020)
- [Fast Human Pose Estimation](https://mlsanity.com/paper/1811.05419/) (2018)
- [Deep Model Compression: Distilling Knowledge from Noisy Teachers](https://mlsanity.com/paper/1610.09650/) (2016)
- [Double-Hard Debias: Tailoring Word Embeddings for Gender Bias Mitigation](https://mlsanity.com/paper/2005.00965/) (2020)
- [Learning Independent Features with Adversarial Nets for Non-linear ICA](https://mlsanity.com/paper/1710.05050/) (2017)
- [Testing DNN Image Classifiers for Confusion & Bias Errors](https://mlsanity.com/paper/1905.07831/) (2019)
- [Drill-down: Interactive Retrieval of Complex Scenes using Natural Language Queries](https://mlsanity.com/paper/1911.03826/) (2019)
- [Chat-crowd: A Dialog-based Platform for Visual Layout Composition](https://mlsanity.com/paper/1812.04081/) (2018)

## Built on by (most cited first, 6 of 6)

- [Teacher-Student Architecture for Knowledge Distillation: A Survey](https://mlsanity.com/paper/2308.04268/) (2023)
- [Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information](https://mlsanity.com/paper/2401.08732/) (2024)
- [PEER pressure: Model-to-Model Regularization for Single Source Domain Generalization](https://mlsanity.com/paper/2505.12745/) (2025)
- [The Hidden Link Between RLHF and Contrastive Learning](https://mlsanity.com/paper/2506.22578/) (2025)
- [Why does Knowledge Distillation Work? Rethink its Attention and Fidelity Mechanism](https://mlsanity.com/paper/2405.00739/) (2024)
- [Information-Theoretic Criteria for Knowledge Distillation in Multimodal Learning](https://mlsanity.com/paper/2510.13182/) (2025)

## Abstract (arXiv)

In this work, we propose Mutual Information Maximization Knowledge Distillation (MIMKD). Our method uses a contrastive objective to simultaneously estimate and maximize a lower bound on the mutual information of local and global feature representations between a teacher and a student network. We demonstrate through extensive experiments that this can be used to improve the performance of low capacity models by transferring knowledge from more performant but computationally expensive models. This can be used to produce better models that can be run on devices with low computational resources. Our method is flexible, we can distill knowledge from teachers with arbitrary network architectures to arbitrary student networks. Our empirical results show that MIMKD outperforms competing approaches across a wide range of student-teacher pairs with different capacities, with different architectures, and when student networks are with extremely low capacity. We are able to obtain 74.55% accuracy on CIFAR100 with a ShufflenetV2 from a baseline accuracy of 69.8% by distilling knowledge from ResNet-50. On Imagenet we improve a ResNet-18 network from 68.88% to 70.32% accuracy (1.44%+) using a ResNet-34 teacher network.