An optimized federated learning method based on soft label grouping for heterogeneous IoT

In the Internet of Things (IoT), a large number of devices generate data. Federated learning can take advantage of the distributional nature of these devices to parallelize model training, thus speeding up model training. The data used for model training in IoT can be heterogeneous, which can greatly reduce the inference accuracy of the global model. To improve the accuracy of models, we propose a new scheme: for the knowledge transfer process, we utilize soft lables to transfer knowledge between clients, and for the parameter aggregation process, we group all the clients based on the similarity of their soft lables and select one client from each group for aggregation in each round of aggregation, and design its weight when participating in the aggregation based on the reliability of its soft lables. We demonstrate through experimentation that our approach is effective and outperforms previous algorithms, resulting in improved model accuracy.