# Practical Insights into Knowledge Distillation for Pre-Trained Models

arXiv: https://arxiv.org/abs/2402.14922 · HTML: https://mlsanity.com/paper/2402.14922/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in General knowledge distillation methods, one of 12 directions in Knowledge distillation.
- Builds on 19 of its 29 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Placed in

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

## Builds on (most cited first, 19 of 19)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data](https://mlsanity.com/paper/2106.05001/) (2021)
- [FedBE: Making Bayesian Model Ensemble Applicable to Federated Learning](https://mlsanity.com/paper/2009.01974/) (2020)
- [Towards Understanding Knowledge Distillation](https://mlsanity.com/paper/2105.13093/) (2021)
- [Large scale distributed neural network training through online distillation](https://mlsanity.com/paper/1804.03235/) (2018)
- [FedScale: Benchmarking Model and System Performance of Federated Learning at Scale](https://mlsanity.com/paper/2105.11367/) (2021)
- [Distillation-Based Semi-Supervised Federated Learning for Communication-Efficient Collaborative Training with Non-IID Private Data](https://mlsanity.com/paper/2008.06180/) (2020)
- [Parameterized Knowledge Transfer for Personalized Federated Learning](https://mlsanity.com/paper/2111.02862/) (2021)
- [Improving Generalization in Federated Learning by Seeking Flat Minima](https://mlsanity.com/paper/2203.11834/) (2022)
- [Cronus: Robust and Heterogeneous Collaborative Learning with Black-Box Knowledge Transfer](https://mlsanity.com/paper/1912.11279/) (2019)
- [FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning](https://mlsanity.com/paper/2102.02514/) (2021)
- [Decentralized Federated Learning through Proxy Model Sharing](https://mlsanity.com/paper/2111.11343/) (2021)
- [FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion](https://mlsanity.com/paper/2110.11027/) (2021)
- [Decentralized Federated Learning via Mutual Knowledge Transfer](https://mlsanity.com/paper/2012.13063/) (2020)
- [Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model](https://mlsanity.com/paper/2310.17653/) (2023)

## Built on by (most cited first, 2 of 2)

- [InFiConD: Interactive No-code Fine-tuning with Concept-based Knowledge Distillation](https://mlsanity.com/paper/2406.17838/) (2024)
- [Query-based Knowledge Transfer for Heterogeneous Learning Environments](https://mlsanity.com/paper/2504.09205/) (2025)

## Abstract (arXiv)

This research investigates the enhancement of knowledge distillation (KD) processes in pre-trained models, an emerging field in knowledge transfer with significant implications for distributed training and federated learning environments. These environments benefit from reduced communication demands and accommodate various model architectures. Despite the adoption of numerous KD approaches for transferring knowledge among pre-trained models, a comprehensive understanding of KD's application in these scenarios is lacking. Our study conducts an extensive comparison of multiple KD techniques, including standard KD, tuned KD (via optimized temperature and weight parameters), deep mutual learning, and data partitioning KD. We assess these methods across various data distribution strategies to identify the most effective contexts for each. Through detailed examination of hyperparameter tuning, informed by extensive grid search evaluations, we pinpoint when adjustments are crucial to enhance model performance. This paper sheds light on optimal hyperparameter settings for distinct data partitioning scenarios and investigates KD's role in improving federated learning by minimizing communication rounds and expediting the training process. By filling a notable void in current research, our findings serve as a practical framework for leveraging KD in pre-trained models within collaborative and federated learning frameworks.