Dirichlet-based Uncertainty Quantification for Personalized Federated Learning with Improved Posterior Networks
This addresses the challenge of data heterogeneity in federated learning for clients needing reliable predictions, though it is incremental as it builds on existing personalized methods.
The paper tackles the problem of unreliable personalized models in federated learning when faced with atypical data, by introducing a method that selects between global and personalized models based on predictive uncertainties. The result shows superior performance on out-of-distribution data while matching state-of-the-art in standard scenarios.
In modern federated learning, one of the main challenges is to account for inherent heterogeneity and the diverse nature of data distributions for different clients. This problem is often addressed by introducing personalization of the models towards the data distribution of the particular client. However, a personalized model might be unreliable when applied to the data that is not typical for this client. Eventually, it may perform worse for these data than the non-personalized global model trained in a federated way on the data from all the clients. This paper presents a new approach to federated learning that allows selecting a model from global and personalized ones that would perform better for a particular input point. It is achieved through a careful modeling of predictive uncertainties that helps to detect local and global in- and out-of-distribution data and use this information to select the model that is confident in a prediction. The comprehensive experimental evaluation on the popular real-world image datasets shows the superior performance of the model in the presence of out-of-distribution data while performing on par with state-of-the-art personalized federated learning algorithms in the standard scenarios.