An Adaptive Clustering Scheme for Client Selections in Communication-Efficient Federated Learning
This work addresses communication efficiency in federated learning, which is crucial for resource-constrained environments, but it is incremental as it builds on existing clustering methods.
The paper tackles the problem of high communication costs in federated learning by proposing an adaptive clustering scheme to dynamically adjust the number of clusters for client selection, reducing communication costs by almost 50% without affecting model accuracy on a non-IID handwritten digit recognition dataset.
Federated learning is a novel decentralized learning architecture. During the training process, the client and server must continuously upload and receive model parameters, which consumes a lot of network transmission resources. Some methods use clustering to find more representative customers, select only a part of them for training, and at the same time ensure the accuracy of training. However, in federated learning, it is not trivial to know what the number of clusters can bring the best training result. Therefore, we propose to dynamically adjust the number of clusters to find the most ideal grouping results. It may reduce the number of users participating in the training to achieve the effect of reducing communication costs without affecting the model performance. We verify its experimental results on the non-IID handwritten digit recognition dataset and reduce the cost of communication and transmission by almost 50% compared with traditional federated learning without affecting the accuracy of the model.