Open yashmaurya01 opened 10 months ago
Hi @yashmaurya01 , how is it going? Let me know if I can help to kickstart the process of creating the FedHe
baseline. We have detailed instructions on how to create a new Flower Baseline in the documentation: https://flower.dev/docs/baselines/how-to-contribute-baselines.html
Paper
FedHe: Heterogeneous Models and Communication-Efficient Federated Learning
Link
https://arxiv.org/abs/2110.09910
Maybe give motivations about why the paper should be implemented as a baseline.
FL typically assumes that all edge devices share the same machine learning model during training, such as an identical neural network architecture. However, in reality, the computational and storage capabilities of various devices may differ. Furthermore, minimizing communication overhead is a challenging task but crucial for enhancing training efficiency in FL. In their research, the authors introduce a novel FL technique known as FedHe, which draws inspiration from knowledge distillation. This approach enables the training of diverse models and facilitates asynchronous training processes while significantly reducing communication overhead. The analysis and experimental results presented in their paper indicate that their method outperforms state-of-the-art algorithms in terms of both communication overhead and model accuracy.
Key Points:
Is there something else you want to add?
No response
Implementation
To implement this baseline, it is recommended to do the following items in that order:
For first time contributors
first contribution
docPrepare - understand the scope
__init__.py
files and aREADME.md
)Implement - make it work
dataset.py
(doesn’t have to match the paper exactly)Align - make it converge