# Digital Twin-Assisted Knowledge Distillation Framework for Heterogeneous Federated Learning

arXiv: https://arxiv.org/abs/2303.06155 · HTML: https://mlsanity.com/paper/2303.06155/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Federated, robust and private distillation, one of 12 directions in Knowledge distillation.
- Builds on 20 of its 51 references that are in the map.
- First posted on arXiv 10 Mar 2023.

## Placed in

- Knowledge distillation / [Federated, robust and private distillation](https://mlsanity.com/distill/federated-robust-and-private-distillation/)

## Builds on (most cited first, 20 of 20)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [On the Convergence of FedAvg on Non-IID Data](https://mlsanity.com/paper/1907.02189/) (2019)
- [Federated Learning with Non-IID Data](https://mlsanity.com/paper/1806.00582/) (2018)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Federated Learning with Personalization Layers](https://mlsanity.com/paper/1912.00818/) (2019)
- [FedMD: Heterogenous Federated Learning via Model Distillation](https://mlsanity.com/paper/1910.03581/) (2019)
- [Robust and Communication-Efficient Federated Learning from Non-IID Data](https://mlsanity.com/paper/1903.02891/) (2019)
- [Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks](https://mlsanity.com/paper/2004.05937/) (2020)
- [SplitFed: When Federated Learning Meets Split Learning](https://mlsanity.com/paper/2004.12088/) (2020)
- [Cross-Layer Distillation with Semantic Calibration](https://mlsanity.com/paper/2012.03236/) (2020)
- [Knowledge Distillation with the Reused Teacher Classifier](https://mlsanity.com/paper/2203.14001/) (2022)
- [Distilled One-Shot Federated Learning](https://mlsanity.com/paper/2009.07999/) (2020)
- [Layer-wised Model Aggregation for Personalized Federated Learning](https://mlsanity.com/paper/2205.03993/) (2022)
- [Detailed comparison of communication efficiency of split learning and federated learning](https://mlsanity.com/paper/1909.09145/) (2019)
- [Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation](https://mlsanity.com/paper/2101.00787/) (2021)
- [Digital Twin-Assisted Efficient Reinforcement Learning for Edge Task Scheduling](https://mlsanity.com/paper/2208.01781/) (2022)
- [Cybertwin: An Origin of Next Generation Network Architecture](https://mlsanity.com/paper/1904.11313/) (2019)
- [On-Demand Resource Management for 6G Wireless Networks Using Knowledge-Assisted Dynamic Neural Networks](https://mlsanity.com/paper/2208.01785/) (2022)

## Built on by (most cited first, 3 of 3)

- [Federated Distillation: A Survey](https://mlsanity.com/paper/2404.08564/) (2024)
- [Imperfect Digital Twin Assisted Low Cost Reinforcement Training for Multi-UAV Networks](https://mlsanity.com/paper/2310.16302/) (2023)
- [Effectively Heterogeneous Federated Learning: A Pairing and Split Learning Based Approach](https://mlsanity.com/paper/2308.13849/) (2023)

## Abstract (arXiv)

In this paper, to deal with the heterogeneity in federated learning (FL) systems, a knowledge distillation (KD) driven training framework for FL is proposed, where each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private dataset. To overcome the challenge of train the big teacher model in resource limited user devices, the digital twin (DT) is exploit in the way that the teacher model can be trained at DT located in the server with enough computing resources. Then, during model distillation, each user can update the parameters of its model at either the physical entity or the digital agent. The joint problem of model selection and training offloading and resource allocation for users is formulated as a mixed integer programming (MIP) problem. To solve the problem, Q-learning and optimization are jointly used, where Q-learning selects models for users and determines whether to train locally or on the server, and optimization is used to allocate resources for users based on the output of Q-learning. Simulation results show the proposed DT-assisted KD framework and joint optimization method can significantly improve the average accuracy of users while reducing the total delay.