I have trained a CNN for the CIFAR dataset using federated averaging, adhering to this tutorial: https://www.tensorflow.org/federated/tutorials/federated_learning_for_image_classification. However, my results are subpar. The problem can be seen in the confusion matrix: 
Based on the confusion matrix, the model seems to be highly biased towards the "airplane" class. Do you have any suggestions as to why this could be the case, or any ideas on how to troubleshoot this? I have tried several hyperparameter combinations, but they all seem to produce similar results.
