# Group Knowledge Transfer: Federated Learning of Large CNNs at the Edge

arXiv: https://arxiv.org/abs/2007.14513 · HTML: https://mlsanity.com/paper/2007.14513/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jul 2020.

## Built on by (most cited first, 10 of 10)

- [Parameterized Knowledge Transfer for Personalized Federated Learning](https://mlsanity.com/paper/2111.02862/) (2021)
- [Cross-Node Federated Graph Neural Network for Spatio-Temporal Data Modeling](https://mlsanity.com/paper/2106.05223/) (2021)
- [From Distributed Machine Learning to Federated Learning: A Survey](https://mlsanity.com/paper/2104.14362/) (2021)
- [Federated Learning for Internet of Things: Applications, Challenges, and Opportunities](https://mlsanity.com/paper/2111.07494/) (2021)
- [A Survey on Heterogeneous Federated Learning](https://mlsanity.com/paper/2210.04505/) (2022)
- [Federated Learning for Healthcare Domain - Pipeline, Applications and Challenges](https://mlsanity.com/paper/2211.07893/) (2022)
- [Specialized federated learning using a mixture of experts](https://mlsanity.com/paper/2010.02056/) (2020)
- [TOFU: Towards Obfuscated Federated Updates by Encoding Weight Updates into Gradients from Proxy Data](https://mlsanity.com/paper/2201.08494/) (2022)
- [A Kernel Perspective on Distillation-based Collaborative Learning](https://mlsanity.com/paper/2410.17592/) (2024)
- [Hyper-parameter Optimization for Federated Learning with Step-wise Adaptive Mechanism](https://mlsanity.com/paper/2411.12244/) (2024)

## Abstract (arXiv)

Scaling up the convolutional neural network (CNN) size (e.g., width, depth, etc.) is known to effectively improve model accuracy. However, the large model size impedes training on resource-constrained edge devices. For instance, federated learning (FL) may place undue burden on the compute capability of edge nodes, even though there is a strong practical need for FL due to its privacy and confidentiality properties. To address the resource-constrained reality of edge devices, we reformulate FL as a group knowledge transfer training algorithm, called FedGKT. FedGKT designs a variant of the alternating minimization approach to train small CNNs on edge nodes and periodically transfer their knowledge by knowledge distillation to a large server-side CNN. FedGKT consolidates several advantages into a single framework: reduced demand for edge computation, lower communication bandwidth for large CNNs, and asynchronous training, all while maintaining model accuracy comparable to FedAvg. We train CNNs designed based on ResNet-56 and ResNet-110 using three distinct datasets (CIFAR-10, CIFAR-100, and CINIC-10) and their non-I.I.D. variants. Our results show that FedGKT can obtain comparable or even slightly higher accuracy than FedAvg. More importantly, FedGKT makes edge training affordable. Compared to the edge training using FedAvg, FedGKT demands 9 to 17 times less computational power (FLOPs) on edge devices and requires 54 to 105 times fewer parameters in the edge CNN. Our source code is released at FedML (https://fedml.ai).