Fig. 8: Performance of methods on the histopathology dataset involving four institutions.
From: Decentralized federated learning through proxy model sharing
For accuracy (a) and macro-averaged accuracy (b) the mean and standard deviation of performance on the test set is recorded at the end of each epoch. Each figure reports mean and standard deviation over 4 clients for each of 15 independent runs. Source data are provided as a Source Data file.
